DEMOThis report is public and visible to anyone with the link for 30 days, then deleted. Save privately — create free account
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_S.gguf
Format: GGUF  ·  Size: 5103.7 MB  ·  Scanned: 2026-09-15  ·  115762 ms
SHA256: 60cccfa9459171215fdd6e2ebff6bf51e26724cd…

Security grade

B
Score: 75/100
2 MEDIUM 3 LOW 4 INFO
Artifact Security
B / 75
Repository Trust
21 / 100
Deployment Confidence
Low
Artifact Security grades the file. Repository Trust reflects HuggingFace repo metadata signals (license, README, popularity). Deployment Confidence combines both.
▶ Score breakdown
Base score 100
MEDIUM Complex agentic chat template — context-dependent risk -8
MEDIUM External URLs embedded in 3 KV metadata field(s) -8
LOW No license field in GGUF metadata (general.license) -3
LOW Fine-tuned model without traceable base_model field -3
LOW 1 weight tensor(s) are >20x the median size: output.weight -3
Penalty subtotal 75/100
Final B / 75
GGUF v3 model | architecture: qwen35 | size: 9B | quantization: Q4_K | 427 tensors | 5 warnings / 4 informational

Runtime compatibility

Runtime Status Quant Architecture Context
llama.cpp
Verify arch support
 ✓ ✓ ?
verify
 256k — may require flash attention (--flash-attn) and large VRAM
Ollama
Verify arch support
 ✓ ✓ ?
verify
 256k — may require flash attention (--flash-attn) and large VRAM
LM Studio
Verify arch support
 ✓ ✓ ?
verify
 256k — may require flash attention (--flash-attn) and large VRAM
vLLM ✗ N/A GGUF not supported — requires safetensors format
HuggingFace Transformers ✗ N/A GGUF not directly supported — use safetensors or PyTorch checkpoint

Model info

Architecture
Neural network family — determines which runtime can load this model
qwen35
NameNyx RP 9B Instruct 2608 v1 OBLITERATED
Size label
Human-readable parameter count from model metadata
9B
Quantization
Weight storage format derived from actual tensor dtypes; lower bits = smaller file and faster inference at the cost of accuracy
 Q4_K
Parameters ~
Estimated total number of weight values; determines VRAM needed at inference
8,953,803,264
Context length
Maximum tokens the model can process in a single prompt+response; affects KV-cache memory
262,144 tokens
Embedding dim
Hidden state dimension (d_model); larger = more expressive but more compute per token
4,096
FFN dim
Feed-forward network intermediate size; typically 2.7–4× embedding_length
12,288
Layers
Number of transformer blocks (depth); more layers = more reasoning capacity
32
Attention heads (Q)
Number of query heads; GQA/MQA models use fewer KV heads than Q heads
16
KV heads
Key/Value heads per layer; fewer than Q heads = GQA; list = per-layer (hybrid architecture)
 4 (GQA: 16 Q → 4 KV)
Vocab size
Number of unique tokens the tokenizer knows; affects embedding table size
248,320
BOS / EOS tokens
Beginning-of-sequence and end-of-sequence token IDs used by the tokenizer
None / 248046
Tokenizer
Tokenizer algorithm family (e.g. gpt2 = BPE, llama = SentencePiece)
gpt2
Chat template
Jinja2 prompt template embedded in model; controls how messages are formatted for inference
✓ Yes — see section below
Fine-tune
Fine-tune descriptor from metadata; indicates this is an adapted version of a base model
Instruct-OBLITERATED
Tensors
Total number of weight tensors stored in the file
427
File size
Size on disk in megabytes
5103.71 MB

Security findings (9)

MEDIUM Metadata Security
Complex agentic chat template — context-dependent risk
Template uses tool_calls, tool responses, namespace() — the full pattern for agentic pipelines. These are legitimate HuggingFace constructs but represent the highest-complexity template class. Risk is context-dependent: negligible for static inference, meaningful in autonomous-agent deployments where user-controlled content can reach the template renderer.
→ Review template before use in agentic pipelines. Use sandboxed Jinja2 rendering and compare against the upstream author's reference template.
MEDIUM Metadata Security
External URLs embedded in 3 KV metadata field(s)
Fields: ['general.base_model.0.repo_url', 'general.url', 'general.source.url']
→ URLs in model metadata may be used for tracking or exfiltration when metadata is rendered; do not auto-fetch
LOW Supply Chain
No license field in GGUF metadata (general.license)
Absence of license information makes it impossible to determine usage rights
→ Add general.license to model metadata before distributing; use an SPDX identifier
LOW Supply Chain
Fine-tuned model without traceable base_model field
Fine-tunes should declare the base model via general.base_model.0 for supply-chain transparency
→ Add general.base_model.0 with the HuggingFace repo of the base model
LOW Statistical Anomaly
1 weight tensor(s) are >20x the median size: output.weight
Extreme outlier tensors may contain embedded payloads or crafted weight matrices
→ Inspect outlier tensor names and compare against reference architecture
INFO Architecture
Grouped Query Attention (GQA) detected
head_count=16, head_count_kv=4 — requires GQA-aware runtime
→ Ensure your runtime (llama.cpp >= b1500, Ollama >= 0.1.30) supports GQA
INFO Architecture
Selective F32 tensors in hybrid/shortconv layers (24 tensors across 24 block(s))
F32 weight tensors in conv1d, ssm layers of a Q4_K-quantized model. Largest: 131,072 B. This is expected in hybrid SSM/shortconv architectures (LFM2, Jamba, Mamba): small conv kernels and state-space projections are kept at full precision because they are numerically sensitive and do not benefit from quantization. Legitimately-F32 tensors (norm/bias/rope/embd): 153.
→ Cross-check against the upstream model checkpoint to confirm these tensors are present in the original. Isolated or large F32 tensors in attention/FFN layers would be more suspicious.
INFO Embedding Size
Large embedding tensor 'token_embd.weight': 572,129,280 bytes
vocab=248,320 x emb_dim=4,096 x 0.5625 B/elem -> expected 572,129,280 B — size is consistent with architecture
→ No action needed; large embeddings are expected for large-vocabulary models
INFO Quantization
Model is quantized: Q4_K, Q5_K, Q6_K
Quantization reduces size and inference cost at the expense of some accuracy
→ Verify the quantization level is appropriate for your use case (Q4_K_M is a common balanced choice)

Integrity & Structure

SHA-25660cccfa9459171215fdd6e2ebff6bf51e26724cd0575c803c552d3fdc71f2694
SHA-512704dc6840c8f0328de2edd7453770d824bd1908b6f05de460ac70087a5aa886bc221fd7d882bb395…
File size (bytes)5,351,629,408
Header + KV + tensor directory10,967,648 bytes (10.46 MB)
Tensor data region5,340,661,760 bytes (5093.25 MB)
Trailing bytes0
Unaccounted bytes0 ✓
KV metadata keys53
Tensors parsed427
Offsets monotone✓ OK
Max tensor offset5,340,645,376

DType Mix

DTypeCountTotal bytesTotal MBAvg bits/elem
Q4_K 241 4,291,559,424 4092.75 4.5
Q6_K 1 834,355,200 795.7 6.5625
Q5_K 8 210,501,632 200.75 5.5
F32 177 4,245,504 4.05 32.0

Chat Template

tokenizer.chat_template (6571 chars) — click to collapse 
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
    {%- if content is string %}
        {{- content }}
    {%- elif content is iterable and content is not mapping %}
        {%- for item in content %}
            {%- if 'text' in item %}
                {{- item.text }}
            {%- else %}
                {{- raise_exception('Unexpected item type in content.') }}
            {%- endif %}
        {%- endfor %}
    {%- elif content is none or content is undefined %}
        {{- '' }}
    {%- else %}
        {{- raise_exception('Unexpected content type.') }}
    {%- endif %}
{%- endmacro %}
{%- if not messages %}
    {{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
    {{- '<|im_start|>system\n' }}
    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
    {%- for tool in tools %}
        {{- "\n" }}
        {{- tool | tojson }}
    {%- endfor %}
    {{- "\n</tools>" }}
    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
    {%- if messages[0].role == 'system' %}
        {%- set content = render_content(messages[0].content, false, true)|trim %}
        {%- if content %}
            {{- '\n\n' + content }}
        {%- endif %}
    {%- endif %}
    {{- '<|im_end|>\n' }}
{%- else %}
    {%- if messages[0].role == 'system' %}
        {%- set content = render_content(messages[0].content, false, true)|trim %}
        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
    {%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
    {%- set index = (messages|length - 1) - loop.index0 %}
    {%- if ns.multi_step_tool and message.role == "user" %}
        {%- set content = render_content(message.content, false)|trim %}
        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
            {%- set ns.multi_step_tool = false %}
            {%- set ns.last_query_index = index %}
        {%- endif %}
    {%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
    {{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
    {%- set content = render_content(message.content, true)|trim %}
    {%- if message.role == "system" %}
        {%- if not loop.first %}
            {{- raise_exception('System message must be at the beginning.') }}
        {%- endif %}
    {%- elif message.role == "user" %}
        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
    {%- elif message.role == "assistant" %}
        {%- set reasoning_content = '' %}
        {%- if message.reasoning_content is string %}
            {%- set reasoning_content = message.reasoning_content %}
        {%- else %}
            {%- if '</think>' in content %}
                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
            {%- endif %}
        {%- endif %}
        {%- set reasoning_content = reasoning_content|trim %}
        {%- if loop.index0 > ns.last_query_index %}
            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
        {%- else %}
            {{- '<|im_start|>' + message.role + '\n' + content }}
        {%- endif %}
        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
            {%- for tool_call in message.tool_calls %}
                {%- if tool_call.function is defined %}
                    {%- set tool_call = tool_call.function %}
                {%- endif %}
                {%- if loop.first %}
                    {%- if content|trim %}
                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
                    {%- else %}
                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
                    {%- endif %}
                {%- else %}
                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
                {%- endif %}
                {%- if tool_call.arguments is mapping %}
                    {%- for args_name in tool_call.arguments %}
                        {%- set args_value = tool_call.arguments[args_name] %}
                        {{- '<parameter=' + args_name + '>\n' }}
                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
                        {{- args_value }}
                        {{- '\n</parameter>\n' }}
                    {%- endfor %}
                {%- endif %}
                {{- '</function>\n</tool_call>' }}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- elif message.role == "tool" %}
        {%- if loop.previtem and loop.previtem.role != "tool" %}
            {{- '<|im_start|>user' }}
        {%- endif %}
        {{- '\n<tool_response>\n' }}
        {{- content }}
        {{- '\n</tool_response>' }}
        {%- if not loop.last and loop.nextitem.role != "tool" %}
            {{- '<|im_end|>\n' }}
        {%- elif loop.last %}
            {{- '<|im_end|>\n' }}
        {%- endif %}
    {%- else %}
        {{- raise_exception('Unexpected message role.') }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|im_start|>assistant\n' }}
    {%- if enable_thinking is defined and enable_thinking is true %}
        {{- '<think>\n' }}
    {%- else %}
        {{- '<think>\n\n</think>\n\n' }}
    {%- endif %}
{%- endif %}

This is a prompt template (non-executable). If your application implements tool-calling agents, enforce a whitelist + schema validation for any <tool_call> output.

Tensor Preview (first 50 of 427)

#NameDimsDTypeOffsetBytesbits/elem
0 output.weight [4096, 248320] Q6_K 0 834,355,200 6.5625
1 output_norm.weight [4096] F32 834,355,200 16,384 32.0
2 token_embd.weight [4096, 248320] Q4_K 834,371,584 572,129,280 4.5
3 blk.0.attn_gate.weight [4096, 4096] Q4_K 1,406,500,864 9,437,184 4.5
4 blk.0.attn_norm.weight [4096] F32 1,415,938,048 16,384 32.0
5 blk.0.attn_qkv.weight [4096, 8192] Q5_K 1,415,954,432 23,068,672 5.5
6 blk.0.ffn_down.weight [12288, 4096] Q5_K 1,439,023,104 34,603,008 5.5
7 blk.0.ffn_gate.weight [4096, 12288] Q4_K 1,473,626,112 28,311,552 4.5
8 blk.0.ffn_up.weight [4096, 12288] Q4_K 1,501,937,664 28,311,552 4.5
9 blk.0.post_attention_norm.weight [4096] F32 1,530,249,216 16,384 32.0
10 blk.0.ssm_a [32] F32 1,530,265,600 128 32.0
11 blk.0.ssm_alpha.weight [4096, 32] Q4_K 1,530,265,728 73,728 4.5
12 blk.0.ssm_beta.weight [4096, 32] Q4_K 1,530,339,456 73,728 4.5
13 blk.0.ssm_conv1d.weight [4, 8192] F32 1,530,413,184 131,072 32.0
14 blk.0.ssm_dt.bias [32] F32 1,530,544,256 128 32.0
15 blk.0.ssm_norm.weight [128] F32 1,530,544,384 512 32.0
16 blk.0.ssm_out.weight [4096, 4096] Q4_K 1,530,544,896 9,437,184 4.5
17 blk.1.attn_gate.weight [4096, 4096] Q4_K 1,539,982,080 9,437,184 4.5
18 blk.1.attn_norm.weight [4096] F32 1,549,419,264 16,384 32.0
19 blk.1.attn_qkv.weight [4096, 8192] Q5_K 1,549,435,648 23,068,672 5.5
20 blk.1.ffn_down.weight [12288, 4096] Q5_K 1,572,504,320 34,603,008 5.5
21 blk.1.ffn_gate.weight [4096, 12288] Q4_K 1,607,107,328 28,311,552 4.5
22 blk.1.ffn_up.weight [4096, 12288] Q4_K 1,635,418,880 28,311,552 4.5
23 blk.1.post_attention_norm.weight [4096] F32 1,663,730,432 16,384 32.0
24 blk.1.ssm_a [32] F32 1,663,746,816 128 32.0
25 blk.1.ssm_alpha.weight [4096, 32] Q4_K 1,663,746,944 73,728 4.5
26 blk.1.ssm_beta.weight [4096, 32] Q4_K 1,663,820,672 73,728 4.5
27 blk.1.ssm_conv1d.weight [4, 8192] F32 1,663,894,400 131,072 32.0
28 blk.1.ssm_dt.bias [32] F32 1,664,025,472 128 32.0
29 blk.1.ssm_norm.weight [128] F32 1,664,025,600 512 32.0
30 blk.1.ssm_out.weight [4096, 4096] Q4_K 1,664,026,112 9,437,184 4.5
31 blk.2.attn_gate.weight [4096, 4096] Q4_K 1,673,463,296 9,437,184 4.5
32 blk.2.attn_norm.weight [4096] F32 1,682,900,480 16,384 32.0
33 blk.2.attn_qkv.weight [4096, 8192] Q5_K 1,682,916,864 23,068,672 5.5
34 blk.2.ffn_down.weight [12288, 4096] Q5_K 1,705,985,536 34,603,008 5.5
35 blk.2.ffn_gate.weight [4096, 12288] Q4_K 1,740,588,544 28,311,552 4.5
36 blk.2.ffn_up.weight [4096, 12288] Q4_K 1,768,900,096 28,311,552 4.5
37 blk.2.post_attention_norm.weight [4096] F32 1,797,211,648 16,384 32.0
38 blk.2.ssm_a [32] F32 1,797,228,032 128 32.0
39 blk.2.ssm_alpha.weight [4096, 32] Q4_K 1,797,228,160 73,728 4.5
40 blk.2.ssm_beta.weight [4096, 32] Q4_K 1,797,301,888 73,728 4.5
41 blk.2.ssm_conv1d.weight [4, 8192] F32 1,797,375,616 131,072 32.0
42 blk.2.ssm_dt.bias [32] F32 1,797,506,688 128 32.0
43 blk.2.ssm_norm.weight [128] F32 1,797,506,816 512 32.0
44 blk.2.ssm_out.weight [4096, 4096] Q4_K 1,797,507,328 9,437,184 4.5
45 blk.3.attn_k.weight [4096, 1024] Q4_K 1,806,944,512 2,359,296 4.5
46 blk.3.attn_k_norm.weight [256] F32 1,809,303,808 1,024 32.0
47 blk.3.attn_norm.weight [4096] F32 1,809,304,832 16,384 32.0
48 blk.3.attn_output.weight [4096, 4096] Q4_K 1,809,321,216 9,437,184 4.5
49 blk.3.attn_q.weight [4096, 8192] Q4_K 1,818,758,400 18,874,368 4.5
… 377 more tensors omitted from preview

HuggingFace Provenance

Repositorymradermacher/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED-i1-GGUF
File pathNyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_S.gguf
Repo commit6f82db3e38edba492361398a5b7b539117cfb75d
README.md✓ present
config.json— not found
tokenizer_config.json— not found
Siblings in repo27 file(s)
Downloads1,572
Likes0
Repo trust score
Heuristic 0–100: license + README + config + download/like signals
 21/100
Tagstransformers, gguf, obliteratus, abliteration, uncensored, obliterate, en, base_model:Muyuxiao/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED, base_model:quantized:Muyuxiao/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED, endpoints_compatible…
All files in repository (27)
FileSize
.gitattributes 0.0 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ1_M.gguf 2744.0 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ1_S.gguf 2615.6 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_M.gguf 3440.4 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_S.gguf 3269.2 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_XS.gguf 3133.1 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_XXS.gguf 2958.0 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_M.gguf 4210.8 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_S.gguf 4168.3 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_XS.gguf 4046.8 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_XXS.gguf 3755.7 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ4_NL.gguf 5167.2 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ4_XS.gguf 4955.7 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q2_K.gguf 3650.0 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q2_K_S.gguf 3526.0 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q3_K_L.gguf 4697.3 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q3_K_M.gguf 4409.3 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q3_K_S.gguf 4062.1 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_0.gguf 5079.2 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_1.gguf 5540.2 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_M.gguf 5368.3 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_S.gguf 5103.7 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q5_K_M.gguf 6168.3 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q5_K_S.gguf 6013.2 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q6_K.gguf 7018.3 MB
Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.imatrix.gguf 4.9 MB
README.md 0.0 MB

Scan coverage

Checks performed
  • ✓Magic bytes &amp; GGUF version validation
  • ✓Header parse (tensor count, KV count)
  • ✓KV metadata parse — all key/value pairs
  • ✓Tensor directory parse (names, dims, dtype, offsets)
  • ✓Tensor offset monotonicity
  • ✓Tensor overlap detection
  • ✓Tensor out-of-bounds detection
  • ✓Data section alignment verification
  • ✓Trailing bytes after last tensor
  • ✓Unaccounted bytes (header vs file size)
  • ✓Dtype histogram &amp; quantization mix analysis
  • ✓Embedding tensor size cross-validation
  • ✓Chat template static scan (Jinja2/SSTI patterns)
  • ✓Runtime compatibility heuristics
  • ✓HuggingFace model card & repository context checked
  • ✓Upstream HuggingFace repository metadata checked
  • ✓Repo identity & commit SHA captured (6f82db3e…)
  • ✓README.md presence checked (✓ present)
  • ✓config.json / tokenizer_config.json presence checked
  • ✓Sibling files enumerated (27 file(s))
  • ✓Downloads / likes / tags captured
  • —Full repository file content audit: not performed
  • —License legal text validation: not performed
Not covered
  • ✗Runtime execution or dynamic analysis
  • ✗Behavioral backdoor detection
  • ✗Weight-level semantic backdoor detection
  • ✗Full upstream repository verification
  • ✗License validation beyond embedded metadata
  • ✗Malware scanning of surrounding repo files
  • ✗Adversarial robustness or alignment audit
  • ✗Training data provenance
ⓘ Static scanning can detect structural anomalies and known malicious patterns. It cannot guarantee absence of risk. Treat results as a security signal, not a formal audit.
Raw scan data (.llmscan JSON) 
{
  "compatibility": [
    {
      "arch": null,
      "container": true,
      "context": "256k \u2014 may require flash attention (--flash-attn) and large VRAM",
      "notes": "GGUF v3 container: supported | quant Q4_K: supported | 256k context: requires sufficient VRAM/RAM and --ctx-size flag \u2014 architecture \u0027qwen35\u0027 is uncommon; check runtime release notes for explicit support",
      "quant": true,
      "runtime": "llama.cpp",
      "supported": null
    },
    {
      "arch": null,
      "container": true,
      "context": "256k \u2014 may require flash attention (--flash-attn) and large VRAM",
      "notes": "GGUF via llama.cpp backend: container and quantization supported \u2014 architecture \u0027qwen35\u0027 is uncommon; check runtime release notes for explicit support",
      "quant": true,
      "runtime": "Ollama",
      "supported": null
    },
    {
      "arch": null,
      "container": true,
      "context": "256k \u2014 may require flash attention (--flash-attn) and large VRAM",
      "notes": "GGUF container and quantization supported; GPU/CPU inference \u2014 architecture \u0027qwen35\u0027 is uncommon; check runtime release notes for explicit support",
      "quant": true,
      "runtime": "LM Studio",
      "supported": null
    },
    {
      "arch": null,
      "container": false,
      "context": null,
      "not_supported_msg": "GGUF not supported \u2014 requires safetensors format",
      "notes": "GGUF not supported; requires safetensors format",
      "quant": false,
      "runtime": "vLLM",
      "supported": false
    },
    {
      "arch": null,
      "container": false,
      "context": null,
      "not_supported_msg": "GGUF not directly supported \u2014 use safetensors or PyTorch checkpoint",
      "notes": "GGUF not supported; requires safetensors or PyTorch checkpoint",
      "quant": false,
      "runtime": "HuggingFace Transformers",
      "supported": false
    }
  ],
  "format": "LLM-SCAN",
  "format_version": "1.0",
  "generator": {
    "name": "llmscan-engine",
    "version": "2.0.0"
  },
  "model": {
    "alignment": 32,
    "arch": "qwen35",
    "architecture": "qwen35",
    "basename": "Nyx-RP",
    "block_count": 32,
    "bos_token_id": null,
    "chat_template": "{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if \u0027text\u0027 in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception(\u0027Unexpected item type in content.\u0027) }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- \u0027\u0027 }}\n    {%- else %}\n        {{- raise_exception(\u0027Unexpected content type.\u0027) }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception(\u0027No messages provided.\u0027) }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- \u0027\u003c|im_start|\u003esystem\\n\u0027 }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n\u003ctools\u003e\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n\u003c/tools\u003e\" }}\n    {{- \u0027\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n\u003ctool_call\u003e\\n\u003cfunction=example_function_name\u003e\\n\u003cparameter=example_parameter_1\u003e\\nvalue_1\\n\u003c/parameter\u003e\\n\u003cparameter=example_parameter_2\u003e\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n\u003c/parameter\u003e\\n\u003c/function\u003e\\n\u003c/tool_call\u003e\\n\\n\u003cIMPORTANT\u003e\\nReminder:\\n- Function calls MUST follow the specified format: an inner \u003cfunction=...\u003e\u003c/function\u003e block must be nested within \u003ctool_call\u003e\u003c/tool_call\u003e XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n\u003c/IMPORTANT\u003e\u0027 }}\n    {%- if messages[0].role == \u0027system\u0027 %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- \u0027\\n\\n\u0027 + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n{%- else %}\n    {%- if messages[0].role == \u0027system\u0027 %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- \u0027\u003c|im_start|\u003esystem\\n\u0027 + content + \u0027\u003c|im_end|\u003e\\n\u0027 }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith(\u0027\u003ctool_response\u003e\u0027) and content.endswith(\u0027\u003c/tool_response\u003e\u0027)) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception(\u0027No user query found in messages.\u0027) }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception(\u0027System message must be at the beginning.\u0027) }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- \u0027\u003c|im_start|\u003e\u0027 + message.role + \u0027\\n\u0027 + content + \u0027\u003c|im_end|\u003e\u0027 + \u0027\\n\u0027 }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = \u0027\u0027 %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if \u0027\u003c/think\u003e\u0027 in content %}\n                {%- set reasoning_content = content.split(\u0027\u003c/think\u003e\u0027)[0].rstrip(\u0027\\n\u0027).split(\u0027\u003cthink\u003e\u0027)[-1].lstrip(\u0027\\n\u0027) %}\n                {%- set content = content.split(\u0027\u003c/think\u003e\u0027)[-1].lstrip(\u0027\\n\u0027) %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 \u003e ns.last_query_index %}\n            {{- \u0027\u003c|im_start|\u003e\u0027 + message.role + \u0027\\n\u003cthink\u003e\\n\u0027 + reasoning_content + \u0027\\n\u003c/think\u003e\\n\\n\u0027 + content }}\n        {%- else %}\n            {{- \u0027\u003c|im_start|\u003e\u0027 + message.role + \u0027\\n\u0027 + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- \u0027\\n\\n\u003ctool_call\u003e\\n\u003cfunction=\u0027 + tool_call.name + \u0027\u003e\\n\u0027 }}\n                    {%- else %}\n                        {{- \u0027\u003ctool_call\u003e\\n\u003cfunction=\u0027 + tool_call.name + \u0027\u003e\\n\u0027 }}\n                    {%- endif %}\n                {%- else %}\n                    {{- \u0027\\n\u003ctool_call\u003e\\n\u003cfunction=\u0027 + tool_call.name + \u0027\u003e\\n\u0027 }}\n                {%- endif %}\n                {%- if tool_call.arguments is mapping %}\n                    {%- for args_name in tool_call.arguments %}\n                        {%- set args_value = tool_call.arguments[args_name] %}\n                        {{- \u0027\u003cparameter=\u0027 + args_name + \u0027\u003e\\n\u0027 }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- \u0027\\n\u003c/parameter\u003e\\n\u0027 }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- \u0027\u003c/function\u003e\\n\u003c/tool_call\u003e\u0027 }}\n            {%- endfor %}\n        {%- endif %}\n        {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- \u0027\u003c|im_start|\u003euser\u0027 }}\n        {%- endif %}\n        {{- \u0027\\n\u003ctool_response\u003e\\n\u0027 }}\n        {{- content }}\n        {{- \u0027\\n\u003c/tool_response\u003e\u0027 }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n        {%- elif loop.last %}\n            {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception(\u0027Unexpected message role.\u0027) }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- \u0027\u003c|im_start|\u003eassistant\\n\u0027 }}\n    {%- if enable_thinking is defined and enable_thinking is true %}\n        {{- \u0027\u003cthink\u003e\\n\u0027 }}\n    {%- else %}\n        {{- \u0027\u003cthink\u003e\\n\\n\u003c/think\u003e\\n\\n\u0027 }}\n    {%- endif %}\n{%- endif %}",
    "context_length": 262144,
    "dtype_histogram": {
      "F32": 177,
      "Q4_K": 241,
      "Q5_K": 8,
      "Q6_K": 1
    },
    "dtype_percentage": {
      "F32": 41.5,
      "Q4_K": 56.4,
      "Q5_K": 1.9,
      "Q6_K": 0.2
    },
    "dtype_stats": {
      "F32": {
        "avg_bits_per_elem": 32.0,
        "bytes": 4245504,
        "count": 177,
        "mb": 4.05
      },
      "Q4_K": {
        "avg_bits_per_elem": 4.5,
        "bytes": 4291559424,
        "count": 241,
        "mb": 4092.75
      },
      "Q5_K": {
        "avg_bits_per_elem": 5.5,
        "bytes": 210501632,
        "count": 8,
        "mb": 200.75
      },
      "Q6_K": {
        "avg_bits_per_elem": 6.5625,
        "bytes": 834355200,
        "count": 1,
        "mb": 795.7
      }
    },
    "embedding_length": 4096,
    "eos_token_id": 248046,
    "feed_forward_length": 12288,
    "file_size_bytes": 5351629408,
    "file_size_mb": 5103.71,
    "finetune": "Instruct-OBLITERATED",
    "format": "gguf",
    "gguf_version": 3,
    "has_chat_template": true,
    "head_count": 16,
    "head_count_kv": 4,
    "header_kv_dir_bytes": 10967648,
    "kv_count": 53,
    "kv_meta": {
      "keys": [
        "general.architecture",
        "general.base_model.0.name",
        "general.base_model.0.organization",
        "general.base_model.0.repo_url",
        "general.base_model.0.version",
        "general.base_model.count",
        "general.basename",
        "general.file_type",
        "general.finetune",
        "general.languages",
        "general.name",
        "general.quantization_version",
        "general.size_label",
        "general.source.url",
        "general.tags",
        "general.type",
        "general.url",
        "general.version",
        "mradermacher.convert_type",
        "mradermacher.quantize_version",
        "mradermacher.quantized_at",
        "mradermacher.quantized_by",
        "mradermacher.quantized_on",
        "quantize.imatrix.chunks_count",
        "quantize.imatrix.dataset",
        "quantize.imatrix.entries_count",
        "quantize.imatrix.file",
        "qwen35.attention.head_count",
        "qwen35.attention.head_count_kv",
        "qwen35.attention.key_length",
        "qwen35.attention.layer_norm_rms_epsilon",
        "qwen35.attention.value_length",
        "qwen35.block_count",
        "qwen35.context_length",
        "qwen35.embedding_length",
        "qwen35.feed_forward_length",
        "qwen35.full_attention_interval",
        "qwen35.rope.dimension_count",
        "qwen35.rope.dimension_sections",
        "qwen35.rope.freq_base",
        "qwen35.ssm.conv_kernel",
        "qwen35.ssm.group_count",
        "qwen35.ssm.inner_size",
        "qwen35.ssm.state_size",
        "qwen35.ssm.time_step_rank",
        "tokenizer.chat_template",
        "tokenizer.ggml.eos_token_id",
        "tokenizer.ggml.merges",
        "tokenizer.ggml.model",
        "tokenizer.ggml.padding_token_id",
        "tokenizer.ggml.pre",
        "tokenizer.ggml.token_type",
        "tokenizer.ggml.tokens"
      ],
      "kv_count": 53,
      "values_redacted": true
    },
    "license": null,
    "max_tensor_offset": 5340645376,
    "misaligned_tensors": 0,
    "model_name": "Nyx RP 9B Instruct 2608 v1 OBLITERATED",
    "offsets_monotone": true,
    "oob_tensor_count": 0,
    "overlapping_tensor_pairs": 0,
    "param_estimate": 8953803264,
    "params_estimate": 8953803264,
    "quantization": "Q4_K",
    "scanner_model_info": {
      "alignment": 32,
      "architecture": "qwen35",
      "basename": "Nyx-RP",
      "block_count": 32,
      "bos_token_id": null,
      "chat_template": "{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if \u0027text\u0027 in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception(\u0027Unexpected item type in content.\u0027) }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- \u0027\u0027 }}\n    {%- else %}\n        {{- raise_exception(\u0027Unexpected content type.\u0027) }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception(\u0027No messages provided.\u0027) }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- \u0027\u003c|im_start|\u003esystem\\n\u0027 }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n\u003ctools\u003e\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n\u003c/tools\u003e\" }}\n    {{- \u0027\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n\u003ctool_call\u003e\\n\u003cfunction=example_function_name\u003e\\n\u003cparameter=example_parameter_1\u003e\\nvalue_1\\n\u003c/parameter\u003e\\n\u003cparameter=example_parameter_2\u003e\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n\u003c/parameter\u003e\\n\u003c/function\u003e\\n\u003c/tool_call\u003e\\n\\n\u003cIMPORTANT\u003e\\nReminder:\\n- Function calls MUST follow the specified format: an inner \u003cfunction=...\u003e\u003c/function\u003e block must be nested within \u003ctool_call\u003e\u003c/tool_call\u003e XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n\u003c/IMPORTANT\u003e\u0027 }}\n    {%- if messages[0].role == \u0027system\u0027 %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- \u0027\\n\\n\u0027 + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n{%- else %}\n    {%- if messages[0].role == \u0027system\u0027 %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- \u0027\u003c|im_start|\u003esystem\\n\u0027 + content + \u0027\u003c|im_end|\u003e\\n\u0027 }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith(\u0027\u003ctool_response\u003e\u0027) and content.endswith(\u0027\u003c/tool_response\u003e\u0027)) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception(\u0027No user query found in messages.\u0027) }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception(\u0027System message must be at the beginning.\u0027) }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- \u0027\u003c|im_start|\u003e\u0027 + message.role + \u0027\\n\u0027 + content + \u0027\u003c|im_end|\u003e\u0027 + \u0027\\n\u0027 }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = \u0027\u0027 %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if \u0027\u003c/think\u003e\u0027 in content %}\n                {%- set reasoning_content = content.split(\u0027\u003c/think\u003e\u0027)[0].rstrip(\u0027\\n\u0027).split(\u0027\u003cthink\u003e\u0027)[-1].lstrip(\u0027\\n\u0027) %}\n                {%- set content = content.split(\u0027\u003c/think\u003e\u0027)[-1].lstrip(\u0027\\n\u0027) %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 \u003e ns.last_query_index %}\n            {{- \u0027\u003c|im_start|\u003e\u0027 + message.role + \u0027\\n\u003cthink\u003e\\n\u0027 + reasoning_content + \u0027\\n\u003c/think\u003e\\n\\n\u0027 + content }}\n        {%- else %}\n            {{- \u0027\u003c|im_start|\u003e\u0027 + message.role + \u0027\\n\u0027 + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- \u0027\\n\\n\u003ctool_call\u003e\\n\u003cfunction=\u0027 + tool_call.name + \u0027\u003e\\n\u0027 }}\n                    {%- else %}\n                        {{- \u0027\u003ctool_call\u003e\\n\u003cfunction=\u0027 + tool_call.name + \u0027\u003e\\n\u0027 }}\n                    {%- endif %}\n                {%- else %}\n                    {{- \u0027\\n\u003ctool_call\u003e\\n\u003cfunction=\u0027 + tool_call.name + \u0027\u003e\\n\u0027 }}\n                {%- endif %}\n                {%- if tool_call.arguments is mapping %}\n                    {%- for args_name in tool_call.arguments %}\n                        {%- set args_value = tool_call.arguments[args_name] %}\n                        {{- \u0027\u003cparameter=\u0027 + args_name + \u0027\u003e\\n\u0027 }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- \u0027\\n\u003c/parameter\u003e\\n\u0027 }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- \u0027\u003c/function\u003e\\n\u003c/tool_call\u003e\u0027 }}\n            {%- endfor %}\n        {%- endif %}\n        {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- \u0027\u003c|im_start|\u003euser\u0027 }}\n        {%- endif %}\n        {{- \u0027\\n\u003ctool_response\u003e\\n\u0027 }}\n        {{- content }}\n        {{- \u0027\\n\u003c/tool_response\u003e\u0027 }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n        {%- elif loop.last %}\n            {{- \u0027\u003c|im_end|\u003e\\n\u0027 }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception(\u0027Unexpected message role.\u0027) }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- \u0027\u003c|im_start|\u003eassistant\\n\u0027 }}\n    {%- if enable_thinking is defined and enable_thinking is true %}\n        {{- \u0027\u003cthink\u003e\\n\u0027 }}\n    {%- else %}\n        {{- \u0027\u003cthink\u003e\\n\\n\u003c/think\u003e\\n\\n\u0027 }}\n    {%- endif %}\n{%- endif %}",
      "context_length": 262144,
      "data_section_start": 10967648,
      "dtype_histogram": {
        "F32": 177,
        "Q4_K": 241,
        "Q5_K": 8,
        "Q6_K": 1
      },
      "dtype_percentage": {
        "F32": 41.5,
        "Q4_K": 56.4,
        "Q5_K": 1.9,
        "Q6_K": 0.2
      },
      "dtype_stats": {
        "F32": {
          "avg_bits_per_elem": 32.0,
          "bytes": 4245504,
          "count": 177,
          "mb": 4.05
        },
        "Q4_K": {
          "avg_bits_per_elem": 4.5,
          "bytes": 4291559424,
          "count": 241,
          "mb": 4092.75
        },
        "Q5_K": {
          "avg_bits_per_elem": 5.5,
          "bytes": 210501632,
          "count": 8,
          "mb": 200.75
        },
        "Q6_K": {
          "avg_bits_per_elem": 6.5625,
          "bytes": 834355200,
          "count": 1,
          "mb": 795.7
        }
      },
      "embedding_length": 4096,
      "eos_token_id": 248046,
      "feed_forward_length": 12288,
      "file_size_bytes": 5351629408,
      "file_size_mb": 5103.71,
      "finetune": "Instruct-OBLITERATED",
      "has_chat_template": true,
      "head_count": 16,
      "head_count_kv": 4,
      "header_end_offset": 10967624,
      "header_kv_dir_bytes": 10967648,
      "kv_count": 53,
      "kv_keys": [
        "general.architecture",
        "general.base_model.0.name",
        "general.base_model.0.organization",
        "general.base_model.0.repo_url",
        "general.base_model.0.version",
        "general.base_model.count",
        "general.basename",
        "general.file_type",
        "general.finetune",
        "general.languages",
        "general.name",
        "general.quantization_version",
        "general.size_label",
        "general.source.url",
        "general.tags",
        "general.type",
        "general.url",
        "general.version",
        "mradermacher.convert_type",
        "mradermacher.quantize_version",
        "mradermacher.quantized_at",
        "mradermacher.quantized_by",
        "mradermacher.quantized_on",
        "quantize.imatrix.chunks_count",
        "quantize.imatrix.dataset",
        "quantize.imatrix.entries_count",
        "quantize.imatrix.file",
        "qwen35.attention.head_count",
        "qwen35.attention.head_count_kv",
        "qwen35.attention.key_length",
        "qwen35.attention.layer_norm_rms_epsilon",
        "qwen35.attention.value_length",
        "qwen35.block_count",
        "qwen35.context_length",
        "qwen35.embedding_length",
        "qwen35.feed_forward_length",
        "qwen35.full_attention_interval",
        "qwen35.rope.dimension_count",
        "qwen35.rope.dimension_sections",
        "qwen35.rope.freq_base",
        "qwen35.ssm.conv_kernel",
        "qwen35.ssm.group_count",
        "qwen35.ssm.inner_size",
        "qwen35.ssm.state_size",
        "qwen35.ssm.time_step_rank",
        "tokenizer.chat_template",
        "tokenizer.ggml.eos_token_id",
        "tokenizer.ggml.merges",
        "tokenizer.ggml.model",
        "tokenizer.ggml.padding_token_id",
        "tokenizer.ggml.pre",
        "tokenizer.ggml.token_type",
        "tokenizer.ggml.tokens"
      ],
      "license": null,
      "magic": "GGUF",
      "max_tensor_offset": 5340645376,
      "misaligned_tensors": 0,
      "model_name": "Nyx RP 9B Instruct 2608 v1 OBLITERATED",
      "offsets_monotone": true,
      "oob_tensor_count": 0,
      "overlapping_tensor_pairs": 0,
      "param_estimate": 8953803264,
      "quantization": "Q4_K",
      "sha256": "60cccfa9459171215fdd6e2ebff6bf51e26724cd0575c803c552d3fdc71f2694",
      "sha512": "704dc6840c8f0328de2edd7453770d824bd1908b6f05de460ac70087a5aa886bc221fd7d882bb39548a446a8963a0c5ce708e67c0c2eba3ce78cb2ee92b1bdc8",
      "size_label": "9B",
      "tensor_bytes_sum": 5340661760,
      "tensor_count": 427,
      "tensor_delta_bytes": 10967648,
      "tensor_delta_mb": 10.46,
      "tensor_preview": [
        {
          "bits_per_elem": 6.5625,
          "byte_len": 834355200,
          "dims": [
            4096,
            248320
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 0,
          "name": "output.weight",
          "offset": 0
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 1,
          "name": "output_norm.weight",
          "offset": 834355200
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 572129280,
          "dims": [
            4096,
            248320
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 2,
          "name": "token_embd.weight",
          "offset": 834371584
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 3,
          "name": "blk.0.attn_gate.weight",
          "offset": 1406500864
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 4,
          "name": "blk.0.attn_norm.weight",
          "offset": 1415938048
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 23068672,
          "dims": [
            4096,
            8192
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 5,
          "name": "blk.0.attn_qkv.weight",
          "offset": 1415954432
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 6,
          "name": "blk.0.ffn_down.weight",
          "offset": 1439023104
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 7,
          "name": "blk.0.ffn_gate.weight",
          "offset": 1473626112
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 8,
          "name": "blk.0.ffn_up.weight",
          "offset": 1501937664
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 9,
          "name": "blk.0.post_attention_norm.weight",
          "offset": 1530249216
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 128,
          "dims": [
            32
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 10,
          "name": "blk.0.ssm_a",
          "offset": 1530265600
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 73728,
          "dims": [
            4096,
            32
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 11,
          "name": "blk.0.ssm_alpha.weight",
          "offset": 1530265728
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 73728,
          "dims": [
            4096,
            32
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 12,
          "name": "blk.0.ssm_beta.weight",
          "offset": 1530339456
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 131072,
          "dims": [
            4,
            8192
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 13,
          "name": "blk.0.ssm_conv1d.weight",
          "offset": 1530413184
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 128,
          "dims": [
            32
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 14,
          "name": "blk.0.ssm_dt.bias",
          "offset": 1530544256
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 512,
          "dims": [
            128
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 15,
          "name": "blk.0.ssm_norm.weight",
          "offset": 1530544384
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 16,
          "name": "blk.0.ssm_out.weight",
          "offset": 1530544896
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 17,
          "name": "blk.1.attn_gate.weight",
          "offset": 1539982080
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 18,
          "name": "blk.1.attn_norm.weight",
          "offset": 1549419264
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 23068672,
          "dims": [
            4096,
            8192
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 19,
          "name": "blk.1.attn_qkv.weight",
          "offset": 1549435648
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 20,
          "name": "blk.1.ffn_down.weight",
          "offset": 1572504320
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 21,
          "name": "blk.1.ffn_gate.weight",
          "offset": 1607107328
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 22,
          "name": "blk.1.ffn_up.weight",
          "offset": 1635418880
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 23,
          "name": "blk.1.post_attention_norm.weight",
          "offset": 1663730432
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 128,
          "dims": [
            32
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 24,
          "name": "blk.1.ssm_a",
          "offset": 1663746816
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 73728,
          "dims": [
            4096,
            32
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 25,
          "name": "blk.1.ssm_alpha.weight",
          "offset": 1663746944
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 73728,
          "dims": [
            4096,
            32
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 26,
          "name": "blk.1.ssm_beta.weight",
          "offset": 1663820672
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 131072,
          "dims": [
            4,
            8192
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 27,
          "name": "blk.1.ssm_conv1d.weight",
          "offset": 1663894400
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 128,
          "dims": [
            32
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 28,
          "name": "blk.1.ssm_dt.bias",
          "offset": 1664025472
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 512,
          "dims": [
            128
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 29,
          "name": "blk.1.ssm_norm.weight",
          "offset": 1664025600
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 30,
          "name": "blk.1.ssm_out.weight",
          "offset": 1664026112
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 31,
          "name": "blk.2.attn_gate.weight",
          "offset": 1673463296
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 32,
          "name": "blk.2.attn_norm.weight",
          "offset": 1682900480
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 23068672,
          "dims": [
            4096,
            8192
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 33,
          "name": "blk.2.attn_qkv.weight",
          "offset": 1682916864
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 34,
          "name": "blk.2.ffn_down.weight",
          "offset": 1705985536
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 35,
          "name": "blk.2.ffn_gate.weight",
          "offset": 1740588544
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 36,
          "name": "blk.2.ffn_up.weight",
          "offset": 1768900096
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 37,
          "name": "blk.2.post_attention_norm.weight",
          "offset": 1797211648
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 128,
          "dims": [
            32
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 38,
          "name": "blk.2.ssm_a",
          "offset": 1797228032
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 73728,
          "dims": [
            4096,
            32
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 39,
          "name": "blk.2.ssm_alpha.weight",
          "offset": 1797228160
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 73728,
          "dims": [
            4096,
            32
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 40,
          "name": "blk.2.ssm_beta.weight",
          "offset": 1797301888
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 131072,
          "dims": [
            4,
            8192
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 41,
          "name": "blk.2.ssm_conv1d.weight",
          "offset": 1797375616
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 128,
          "dims": [
            32
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 42,
          "name": "blk.2.ssm_dt.bias",
          "offset": 1797506688
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 512,
          "dims": [
            128
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 43,
          "name": "blk.2.ssm_norm.weight",
          "offset": 1797506816
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 44,
          "name": "blk.2.ssm_out.weight",
          "offset": 1797507328
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 2359296,
          "dims": [
            4096,
            1024
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 45,
          "name": "blk.3.attn_k.weight",
          "offset": 1806944512
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 1024,
          "dims": [
            256
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 46,
          "name": "blk.3.attn_k_norm.weight",
          "offset": 1809303808
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 16384,
          "dims": [
            4096
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 47,
          "name": "blk.3.attn_norm.weight",
          "offset": 1809304832
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 9437184,
          "dims": [
            4096,
            4096
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 48,
          "name": "blk.3.attn_output.weight",
          "offset": 1809321216
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 18874368,
          "dims": [
            4096,
            8192
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 49,
          "name": "blk.3.attn_q.weight",
          "offset": 1818758400
        }
      ],
      "tokenizer_model": "gpt2",
      "top_tensors_by_size": [
        {
          "byte_len": 834355200,
          "dims": [
            4096,
            248320
          ],
          "dtype": "Q6_K",
          "n_elem": 1017118720,
          "name": "output.weight"
        },
        {
          "byte_len": 572129280,
          "dims": [
            4096,
            248320
          ],
          "dtype": "Q4_K",
          "n_elem": 1017118720,
          "name": "token_embd.weight"
        },
        {
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype": "Q5_K",
          "n_elem": 50331648,
          "name": "blk.0.ffn_down.weight"
        },
        {
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype": "Q5_K",
          "n_elem": 50331648,
          "name": "blk.1.ffn_down.weight"
        },
        {
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype": "Q5_K",
          "n_elem": 50331648,
          "name": "blk.2.ffn_down.weight"
        },
        {
          "byte_len": 34603008,
          "dims": [
            12288,
            4096
          ],
          "dtype": "Q5_K",
          "n_elem": 50331648,
          "name": "blk.3.ffn_down.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.0.ffn_gate.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.0.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.1.ffn_gate.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            4096,
            12288
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.1.ffn_up.weight"
        }
      ],
      "trailing_bytes": 0,
      "unaccounted_bytes": 0,
      "version": 3,
      "vocab_size": 248320
    },
    "sha256": "60cccfa9459171215fdd6e2ebff6bf51e26724cd0575c803c552d3fdc71f2694",
    "sha512": "704dc6840c8f0328de2edd7453770d824bd1908b6f05de460ac70087a5aa886bc221fd7d882bb39548a446a8963a0c5ce708e67c0c2eba3ce78cb2ee92b1bdc8",
    "size_label": "9B",
    "tensor_bytes_sum": 5340661760,
    "tensor_count": 427,
    "tensor_delta_bytes": 10967648,
    "tensor_delta_mb": 10.46,
    "tensor_preview": [
      {
        "bits_per_elem": 6.5625,
        "byte_len": 834355200,
        "dims": [
          4096,
          248320
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 0,
        "name": "output.weight",
        "offset": 0
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 1,
        "name": "output_norm.weight",
        "offset": 834355200
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 572129280,
        "dims": [
          4096,
          248320
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 2,
        "name": "token_embd.weight",
        "offset": 834371584
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 3,
        "name": "blk.0.attn_gate.weight",
        "offset": 1406500864
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 4,
        "name": "blk.0.attn_norm.weight",
        "offset": 1415938048
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 23068672,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 5,
        "name": "blk.0.attn_qkv.weight",
        "offset": 1415954432
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 6,
        "name": "blk.0.ffn_down.weight",
        "offset": 1439023104
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 7,
        "name": "blk.0.ffn_gate.weight",
        "offset": 1473626112
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 8,
        "name": "blk.0.ffn_up.weight",
        "offset": 1501937664
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 9,
        "name": "blk.0.post_attention_norm.weight",
        "offset": 1530249216
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 10,
        "name": "blk.0.ssm_a",
        "offset": 1530265600
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 11,
        "name": "blk.0.ssm_alpha.weight",
        "offset": 1530265728
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 12,
        "name": "blk.0.ssm_beta.weight",
        "offset": 1530339456
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 131072,
        "dims": [
          4,
          8192
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 13,
        "name": "blk.0.ssm_conv1d.weight",
        "offset": 1530413184
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 14,
        "name": "blk.0.ssm_dt.bias",
        "offset": 1530544256
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 512,
        "dims": [
          128
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 15,
        "name": "blk.0.ssm_norm.weight",
        "offset": 1530544384
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 16,
        "name": "blk.0.ssm_out.weight",
        "offset": 1530544896
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 17,
        "name": "blk.1.attn_gate.weight",
        "offset": 1539982080
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 18,
        "name": "blk.1.attn_norm.weight",
        "offset": 1549419264
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 23068672,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 19,
        "name": "blk.1.attn_qkv.weight",
        "offset": 1549435648
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 20,
        "name": "blk.1.ffn_down.weight",
        "offset": 1572504320
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 21,
        "name": "blk.1.ffn_gate.weight",
        "offset": 1607107328
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 22,
        "name": "blk.1.ffn_up.weight",
        "offset": 1635418880
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 23,
        "name": "blk.1.post_attention_norm.weight",
        "offset": 1663730432
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 24,
        "name": "blk.1.ssm_a",
        "offset": 1663746816
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 25,
        "name": "blk.1.ssm_alpha.weight",
        "offset": 1663746944
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 26,
        "name": "blk.1.ssm_beta.weight",
        "offset": 1663820672
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 131072,
        "dims": [
          4,
          8192
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 27,
        "name": "blk.1.ssm_conv1d.weight",
        "offset": 1663894400
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 28,
        "name": "blk.1.ssm_dt.bias",
        "offset": 1664025472
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 512,
        "dims": [
          128
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 29,
        "name": "blk.1.ssm_norm.weight",
        "offset": 1664025600
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 30,
        "name": "blk.1.ssm_out.weight",
        "offset": 1664026112
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 31,
        "name": "blk.2.attn_gate.weight",
        "offset": 1673463296
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 32,
        "name": "blk.2.attn_norm.weight",
        "offset": 1682900480
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 23068672,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 33,
        "name": "blk.2.attn_qkv.weight",
        "offset": 1682916864
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 34,
        "name": "blk.2.ffn_down.weight",
        "offset": 1705985536
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 35,
        "name": "blk.2.ffn_gate.weight",
        "offset": 1740588544
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 36,
        "name": "blk.2.ffn_up.weight",
        "offset": 1768900096
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 37,
        "name": "blk.2.post_attention_norm.weight",
        "offset": 1797211648
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 38,
        "name": "blk.2.ssm_a",
        "offset": 1797228032
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 39,
        "name": "blk.2.ssm_alpha.weight",
        "offset": 1797228160
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 40,
        "name": "blk.2.ssm_beta.weight",
        "offset": 1797301888
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 131072,
        "dims": [
          4,
          8192
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 41,
        "name": "blk.2.ssm_conv1d.weight",
        "offset": 1797375616
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 42,
        "name": "blk.2.ssm_dt.bias",
        "offset": 1797506688
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 512,
        "dims": [
          128
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 43,
        "name": "blk.2.ssm_norm.weight",
        "offset": 1797506816
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 44,
        "name": "blk.2.ssm_out.weight",
        "offset": 1797507328
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 2359296,
        "dims": [
          4096,
          1024
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 45,
        "name": "blk.3.attn_k.weight",
        "offset": 1806944512
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 1024,
        "dims": [
          256
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 46,
        "name": "blk.3.attn_k_norm.weight",
        "offset": 1809303808
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 47,
        "name": "blk.3.attn_norm.weight",
        "offset": 1809304832
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 48,
        "name": "blk.3.attn_output.weight",
        "offset": 1809321216
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 18874368,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 49,
        "name": "blk.3.attn_q.weight",
        "offset": 1818758400
      }
    ],
    "tokenizer_model": "gpt2",
    "top_tensors_by_size": [
      {
        "byte_len": 834355200,
        "dims": [
          4096,
          248320
        ],
        "dtype": "Q6_K",
        "n_elem": 1017118720,
        "name": "output.weight"
      },
      {
        "byte_len": 572129280,
        "dims": [
          4096,
          248320
        ],
        "dtype": "Q4_K",
        "n_elem": 1017118720,
        "name": "token_embd.weight"
      },
      {
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype": "Q5_K",
        "n_elem": 50331648,
        "name": "blk.0.ffn_down.weight"
      },
      {
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype": "Q5_K",
        "n_elem": 50331648,
        "name": "blk.1.ffn_down.weight"
      },
      {
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype": "Q5_K",
        "n_elem": 50331648,
        "name": "blk.2.ffn_down.weight"
      },
      {
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype": "Q5_K",
        "n_elem": 50331648,
        "name": "blk.3.ffn_down.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.0.ffn_gate.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.0.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.1.ffn_gate.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.1.ffn_up.weight"
      }
    ],
    "trailing_bytes": 0,
    "unaccounted_bytes": 0,
    "values_redacted": true,
    "vocab_size": 248320
  },
  "report": {
    "bullets": [
      "GGUF v3 model | architecture: qwen35 | size: 9B | quantization: Q4_K | 427 tensors | 5 warnings / 4 informational",
      "Size: 5103.71 MB",
      "SHA256: 60cccfa945917121..."
    ],
    "recommendations": [
      "Review template before use in agentic pipelines. Use sandboxed Jinja2 rendering and compare against the upstream author\u0027s reference template.",
      "URLs in model metadata may be used for tracking or exfiltration when metadata is rendered; do not auto-fetch",
      "Add general.license to model metadata before distributing; use an SPDX identifier",
      "Add general.base_model.0 with the HuggingFace repo of the base model",
      "Inspect outlier tensor names and compare against reference architecture"
    ],
    "summary": "GGUF v3 model | architecture: qwen35 | size: 9B | quantization: Q4_K | 427 tensors | 5 warnings / 4 informational"
  },
  "scan_context": {
    "duration_ms": 115762,
    "ended_at": "2026-09-15T04:54:45+00:00Z",
    "limits": {
      "sandbox": true,
      "timeout_ms": 60000
    },
    "mode": "static-deep",
    "started_at": "2026-09-15T04:54:45+00:00Z"
  },
  "security": {
    "findings": [
      {
        "category": "Architecture",
        "detail": "head_count=16, head_count_kv=4 \u2014 requires GQA-aware runtime",
        "recommendation": "Ensure your runtime (llama.cpp \u003e= b1500, Ollama \u003e= 0.1.30) supports GQA",
        "severity": "INFO",
        "title": "Grouped Query Attention (GQA) detected"
      },
      {
        "category": "Metadata Security",
        "detail": "Template uses tool_calls, tool responses, namespace() \u2014 the full pattern for agentic pipelines. These are legitimate HuggingFace constructs but represent the highest-complexity template class. Risk is context-dependent: negligible for static inference, meaningful in autonomous-agent deployments where user-controlled content can reach the template renderer.",
        "recommendation": "Review template before use in agentic pipelines. Use sandboxed Jinja2 rendering and compare against the upstream author\u0027s reference template.",
        "severity": "MEDIUM",
        "title": "Complex agentic chat template \u2014 context-dependent risk"
      },
      {
        "category": "Metadata Security",
        "detail": "Fields: [\u0027general.base_model.0.repo_url\u0027, \u0027general.url\u0027, \u0027general.source.url\u0027]",
        "recommendation": "URLs in model metadata may be used for tracking or exfiltration when metadata is rendered; do not auto-fetch",
        "severity": "MEDIUM",
        "title": "External URLs embedded in 3 KV metadata field(s)"
      },
      {
        "category": "Supply Chain",
        "detail": "Absence of license information makes it impossible to determine usage rights",
        "recommendation": "Add general.license to model metadata before distributing; use an SPDX identifier",
        "severity": "LOW",
        "title": "No license field in GGUF metadata (general.license)"
      },
      {
        "category": "Supply Chain",
        "detail": "Fine-tunes should declare the base model via general.base_model.0 for supply-chain transparency",
        "recommendation": "Add general.base_model.0 with the HuggingFace repo of the base model",
        "severity": "LOW",
        "title": "Fine-tuned model without traceable base_model field"
      },
      {
        "category": "Architecture",
        "detail": "F32 weight tensors in conv1d, ssm layers of a Q4_K-quantized model. Largest: 131,072 B. This is expected in hybrid SSM/shortconv architectures (LFM2, Jamba, Mamba): small conv kernels and state-space projections are kept at full precision because they are numerically sensitive and do not benefit from quantization. Legitimately-F32 tensors (norm/bias/rope/embd): 153.",
        "recommendation": "Cross-check against the upstream model checkpoint to confirm these tensors are present in the original. Isolated or large F32 tensors in attention/FFN layers would be more suspicious.",
        "severity": "INFO",
        "title": "Selective F32 tensors in hybrid/shortconv layers (24 tensors across 24 block(s))"
      },
      {
        "category": "Embedding Size",
        "detail": "vocab=248,320 x emb_dim=4,096 x 0.5625 B/elem -\u003e expected 572,129,280 B \u2014 size is consistent with architecture",
        "recommendation": "No action needed; large embeddings are expected for large-vocabulary models",
        "severity": "INFO",
        "title": "Large embedding tensor \u0027token_embd.weight\u0027: 572,129,280 bytes"
      },
      {
        "category": "Statistical Anomaly",
        "detail": "Extreme outlier tensors may contain embedded payloads or crafted weight matrices",
        "recommendation": "Inspect outlier tensor names and compare against reference architecture",
        "severity": "LOW",
        "title": "1 weight tensor(s) are \u003e20x the median size: output.weight"
      },
      {
        "category": "Quantization",
        "detail": "Quantization reduces size and inference cost at the expense of some accuracy",
        "recommendation": "Verify the quantization level is appropriate for your use case (Q4_K_M is a common balanced choice)",
        "severity": "INFO",
        "title": "Model is quantized: Q4_K, Q5_K, Q6_K"
      }
    ],
    "grade": "B",
    "score": 75
  },
  "source": {
    "file_sha": null,
    "filename": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_S.gguf",
    "hashes": {
      "sha256": "60cccfa9459171215fdd6e2ebff6bf51e26724cd0575c803c552d3fdc71f2694"
    },
    "hf_provenance": {
      "downloads": 1572,
      "file_sha": null,
      "has_config": false,
      "has_readme": true,
      "has_tokenizer_config": false,
      "likes": 0,
      "pipeline_tag": null,
      "repo_id": "mradermacher/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED-i1-GGUF",
      "repo_license": null,
      "repo_sha": "6f82db3e38edba492361398a5b7b539117cfb75d",
      "siblings": [
        {
          "name": ".gitattributes",
          "sha": null,
          "size": 3755
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ1_M.gguf",
          "sha": null,
          "size": 2877268576
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ1_S.gguf",
          "sha": null,
          "size": 2742641248
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_M.gguf",
          "sha": null,
          "size": 3607470688
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_S.gguf",
          "sha": null,
          "size": 3427967584
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_XS.gguf",
          "sha": null,
          "size": 3285344864
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ2_XXS.gguf",
          "sha": null,
          "size": 3101647456
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_M.gguf",
          "sha": null,
          "size": 4415382112
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_S.gguf",
          "sha": null,
          "size": 4370817632
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_XS.gguf",
          "sha": null,
          "size": 4243415648
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ3_XXS.gguf",
          "sha": null,
          "size": 3938165344
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ4_NL.gguf",
          "sha": null,
          "size": 5418213984
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-IQ4_XS.gguf",
          "sha": null,
          "size": 5196440160
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q2_K.gguf",
          "sha": null,
          "size": 3827262048
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q2_K_S.gguf",
          "sha": null,
          "size": 3697238624
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q3_K_L.gguf",
          "sha": null,
          "size": 4925514336
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q3_K_M.gguf",
          "sha": null,
          "size": 4623524448
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q3_K_S.gguf",
          "sha": null,
          "size": 4259406432
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_0.gguf",
          "sha": null,
          "size": 5325939296
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_1.gguf",
          "sha": null,
          "size": 5809332832
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_M.gguf",
          "sha": null,
          "size": 5629108832
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q4_K_S.gguf",
          "sha": null,
          "size": 5351629408
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q5_K_M.gguf",
          "sha": null,
          "size": 6467969632
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q5_K_S.gguf",
          "sha": null,
          "size": 6305309280
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.i1-Q6_K.gguf",
          "sha": null,
          "size": 7359259232
        },
        {
          "name": "Nyx-RP-9B-Instruct-2608-v1-OBLITERATED.imatrix.gguf",
          "sha": null,
          "size": 5150176
        },
        {
          "name": "README.md",
          "sha": null,
          "size": 7175
        }
      ],
      "siblings_count": 27,
      "tags": [
        "transformers",
        "gguf",
        "obliteratus",
        "abliteration",
        "uncensored",
        "obliterate",
        "en",
        "base_model:Muyuxiao/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED",
        "base_model:quantized:Muyuxiao/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED",
        "endpoints_compatible",
        "region:us",
        "imatrix",
        "conversational"
      ],
      "trust_score": 21
    },
    "input_type": "huggingface",
    "repo_id": "mradermacher/Nyx-RP-9B-Instruct-2608-v1-OBLITERATED-i1-GGUF",
    "repo_sha": "6f82db3e38edba492361398a5b7b539117cfb75d",
    "size_bytes": 5351629408
  },
  "tensors": {
    "count": 427,
    "dtype_histogram": {
      "F32": 177,
      "Q4_K": 241,
      "Q5_K": 8,
      "Q6_K": 1
    },
    "dtype_stats": {
      "F32": {
        "avg_bits_per_elem": 32.0,
        "bytes": 4245504,
        "count": 177,
        "mb": 4.05
      },
      "Q4_K": {
        "avg_bits_per_elem": 4.5,
        "bytes": 4291559424,
        "count": 241,
        "mb": 4092.75
      },
      "Q5_K": {
        "avg_bits_per_elem": 5.5,
        "bytes": 210501632,
        "count": 8,
        "mb": 200.75
      },
      "Q6_K": {
        "avg_bits_per_elem": 6.5625,
        "bytes": 834355200,
        "count": 1,
        "mb": 795.7
      }
    },
    "integrity": {
      "header_kv_dir_bytes": 10967648,
      "misaligned_tensors": 0,
      "offsets_monotone": true,
      "oob_tensor_count": 0,
      "overlapping_tensor_pairs": 0,
      "tensor_bytes_sum": 5340661760,
      "tensor_delta_bytes": 10967648,
      "tensor_delta_mb": 10.46,
      "trailing_bytes": 0,
      "unaccounted_bytes": 0
    },
    "preview": [
      {
        "bits_per_elem": 6.5625,
        "byte_len": 834355200,
        "dims": [
          4096,
          248320
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 0,
        "name": "output.weight",
        "offset": 0
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 1,
        "name": "output_norm.weight",
        "offset": 834355200
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 572129280,
        "dims": [
          4096,
          248320
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 2,
        "name": "token_embd.weight",
        "offset": 834371584
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 3,
        "name": "blk.0.attn_gate.weight",
        "offset": 1406500864
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 4,
        "name": "blk.0.attn_norm.weight",
        "offset": 1415938048
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 23068672,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 5,
        "name": "blk.0.attn_qkv.weight",
        "offset": 1415954432
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 6,
        "name": "blk.0.ffn_down.weight",
        "offset": 1439023104
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 7,
        "name": "blk.0.ffn_gate.weight",
        "offset": 1473626112
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 8,
        "name": "blk.0.ffn_up.weight",
        "offset": 1501937664
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 9,
        "name": "blk.0.post_attention_norm.weight",
        "offset": 1530249216
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 10,
        "name": "blk.0.ssm_a",
        "offset": 1530265600
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 11,
        "name": "blk.0.ssm_alpha.weight",
        "offset": 1530265728
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 12,
        "name": "blk.0.ssm_beta.weight",
        "offset": 1530339456
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 131072,
        "dims": [
          4,
          8192
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 13,
        "name": "blk.0.ssm_conv1d.weight",
        "offset": 1530413184
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 14,
        "name": "blk.0.ssm_dt.bias",
        "offset": 1530544256
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 512,
        "dims": [
          128
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 15,
        "name": "blk.0.ssm_norm.weight",
        "offset": 1530544384
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 16,
        "name": "blk.0.ssm_out.weight",
        "offset": 1530544896
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 17,
        "name": "blk.1.attn_gate.weight",
        "offset": 1539982080
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 18,
        "name": "blk.1.attn_norm.weight",
        "offset": 1549419264
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 23068672,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 19,
        "name": "blk.1.attn_qkv.weight",
        "offset": 1549435648
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 20,
        "name": "blk.1.ffn_down.weight",
        "offset": 1572504320
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 21,
        "name": "blk.1.ffn_gate.weight",
        "offset": 1607107328
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 22,
        "name": "blk.1.ffn_up.weight",
        "offset": 1635418880
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 23,
        "name": "blk.1.post_attention_norm.weight",
        "offset": 1663730432
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 24,
        "name": "blk.1.ssm_a",
        "offset": 1663746816
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 25,
        "name": "blk.1.ssm_alpha.weight",
        "offset": 1663746944
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 26,
        "name": "blk.1.ssm_beta.weight",
        "offset": 1663820672
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 131072,
        "dims": [
          4,
          8192
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 27,
        "name": "blk.1.ssm_conv1d.weight",
        "offset": 1663894400
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 28,
        "name": "blk.1.ssm_dt.bias",
        "offset": 1664025472
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 512,
        "dims": [
          128
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 29,
        "name": "blk.1.ssm_norm.weight",
        "offset": 1664025600
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 30,
        "name": "blk.1.ssm_out.weight",
        "offset": 1664026112
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 31,
        "name": "blk.2.attn_gate.weight",
        "offset": 1673463296
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 32,
        "name": "blk.2.attn_norm.weight",
        "offset": 1682900480
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 23068672,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 33,
        "name": "blk.2.attn_qkv.weight",
        "offset": 1682916864
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 34603008,
        "dims": [
          12288,
          4096
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 34,
        "name": "blk.2.ffn_down.weight",
        "offset": 1705985536
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 35,
        "name": "blk.2.ffn_gate.weight",
        "offset": 1740588544
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          4096,
          12288
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 36,
        "name": "blk.2.ffn_up.weight",
        "offset": 1768900096
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 37,
        "name": "blk.2.post_attention_norm.weight",
        "offset": 1797211648
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 38,
        "name": "blk.2.ssm_a",
        "offset": 1797228032
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 39,
        "name": "blk.2.ssm_alpha.weight",
        "offset": 1797228160
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 73728,
        "dims": [
          4096,
          32
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 40,
        "name": "blk.2.ssm_beta.weight",
        "offset": 1797301888
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 131072,
        "dims": [
          4,
          8192
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 41,
        "name": "blk.2.ssm_conv1d.weight",
        "offset": 1797375616
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 128,
        "dims": [
          32
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 42,
        "name": "blk.2.ssm_dt.bias",
        "offset": 1797506688
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 512,
        "dims": [
          128
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 43,
        "name": "blk.2.ssm_norm.weight",
        "offset": 1797506816
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 44,
        "name": "blk.2.ssm_out.weight",
        "offset": 1797507328
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 2359296,
        "dims": [
          4096,
          1024
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 45,
        "name": "blk.3.attn_k.weight",
        "offset": 1806944512
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 1024,
        "dims": [
          256
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 46,
        "name": "blk.3.attn_k_norm.weight",
        "offset": 1809303808
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 16384,
        "dims": [
          4096
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 47,
        "name": "blk.3.attn_norm.weight",
        "offset": 1809304832
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 9437184,
        "dims": [
          4096,
          4096
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 48,
        "name": "blk.3.attn_output.weight",
        "offset": 1809321216
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 18874368,
        "dims": [
          4096,
          8192
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 49,
        "name": "blk.3.attn_q.weight",
        "offset": 1818758400
      }
    ]
  },
  "tokenizer": {
    "bos_token_id": null,
    "chat_template_chars": 6571,
    "eos_token_id": 248046,
    "has_chat_template": true,
    "type": "gpt2",
    "vocab_size": 248320
  }
}