Get the app
← back to catalog · registered 2026-08-22 13:56

noneUsername/QwQ-32B-abliterated-AWQ-INT4

noneUsername Qwen 31B second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/noneUsername%2FQwQ-32B-abliterated-AWQ-INT4"
Response includes
  • classification m1
  • files 15
  • hub_downloads_all_time 7,739
  • author_summary 17 models
  • readme_text full
Try next
GET/models?author=noneUsername
All 17 models by noneUsername
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
8K
26 last 30d - cooling
Likes
5
Model age
19mo ago
created 2025-03-08
Downloads over time
Now7.8K→from25↑30,920%
02.8K5.7K8.5K25 on Mar 5, 20257.8K on Oct 11Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 5, 2025 → Oct 11 · 123 snapshots · spans 585 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

huihui-ai/QwQ-32B-abliterated↓ 148 this lineage
noneUsername/QwQ-32B-abliterated-AWQ-INT4↓ 26

Metadata

Tags
safetensors qwen2 base_model:huihui-ai/QwQ-32B-abliterated base_model:quantized:huihui-ai/QwQ-32B-abliterated 4-bit awq region:us

Related

Other by noneUsername
Qwen3-32B-abliterated-awq 3K huihui-ai-phi-4-abliterated-W8A8 20 Mistral-Small-Instruct-2409-abliterated-W8A8-Dynamic-Per-Token 17 Qwen2.5-Coder-14B-Instruct-abliterated-W8A8-Dynamic-Per-Token 17 Phi-3-medium-4k-instruct-abliterated-v3-W8A8-Dynamic-Per-Token 13
Same base model
bartowski/huihui-ai_QwQ-32B-abliterated-GGUF 8K mradermacher/QwQ-32B-abliterated-i1-GGUF 1K DevQuasar-9/huihui-ai.QwQ-32B-abliterated-GGUF 444 mradermacher/QwQ-32B-abliterated-GGUF 372 DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored 35
Total size
18.0 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-08 06:53
Source huggingface.co/noneUsername/QwQ-32B-abliterated-AWQ-INT4 ↗ Base model huihui-ai/QwQ-32B-abliterated →

Files by quantization

Auxiliary files 15 files 18.0 GB
model-00002-of-00004.safetensors 4.65 GB e7ca0800 download
model-00003-of-00004.safetensors 4.62 GB 4017cbc5 download
model-00001-of-00004.safetensors 4.62 GB 9daf54ee download
model-00004-of-00004.safetensors 4.11 GB 35167c7b download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 133 KB d6493abe download
tokenizer_config.json 7.92 KB b27d5264 download
README.md 4.53 KB 69ffc191 download
.gitattributes 1.53 KB 52373fe2 download
config.json 925 B b9ec13f6 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B c045df0c download

README current version from Hugging Face

base_model:

  • huihui-ai/QwQ-32B-abliterated

vllm (pretrained=/root/autodl-tmp/QwQ-32B,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.432 ± 0.0314
strict-match 5 exact_match ↑ 0.744 ± 0.0277

vllm (pretrained=/root/autodl-tmp/QwQ-32B,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.444 ± 0.0222
strict-match 5 exact_match ↑ 0.716 ± 0.0202
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8140 ± 0.0125
- humanities 2 none acc ↑ 0.8359 ± 0.0251
- other 2 none acc ↑ 0.8103 ± 0.0269
- social sciences 2 none acc ↑ 0.8889 ± 0.0222
- stem 2 none acc ↑ 0.7544 ± 0.0238

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.528 ± 0.0316
strict-match 5 exact_match ↑ 0.740 ± 0.0278

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.492 ± 0.0224
strict-match 5 exact_match ↑ 0.742 ± 0.0196

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1

Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8152 ± 0.0126
- humanities 2 none acc ↑ 0.8359 ± 0.0253
- other 2 none acc ↑ 0.8000 ± 0.0276
- social sciences 2 none acc ↑ 0.8722 ± 0.0240
- stem 2 none acc ↑ 0.7754 ± 0.0232

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.476 ± 0.0316
strict-match 5 exact_match ↑ 0.752 ± 0.0274

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.524 ± 0.0224
strict-match 5 exact_match ↑ 0.716 ± 0.0202
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8023 ± 0.0130
- humanities 2 none acc ↑ 0.8000 ± 0.0266
- other 2 none acc ↑ 0.7949 ± 0.0284
- social sciences 2 none acc ↑ 0.8500 ± 0.0258
- stem 2 none acc ↑ 0.7789 ± 0.0235

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2025-03-08Create README.md39444a34.5 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration