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

noneUsername/Qwen3-32B-abliterated-awq

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%2FQwen3-32B-abliterated-awq"
Response includes
  • classification m1
  • files 16
  • hub_downloads_all_time 88,371
  • 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
88K
3K last 30d - cooling
Likes
2
Model age
15mo ago
created 2025-06-22
Downloads over time
Now89.7K→from117↑76,568%
032.9K65.8K98.7K117 on Jul 9, 202589.7K on Oct 11Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 9, 2025 → Oct 11 · 107 snapshots · spans 459 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/Qwen3-32B-abliterated↓ 531 this lineage
noneUsername/Qwen3-32B-abliterated-awq↓ 2,600

Metadata

Tags
safetensors qwen3 base_model:huihui-ai/Qwen3-32B-abliterated base_model:quantized:huihui-ai/Qwen3-32B-abliterated 4-bit awq region:us

Related

Other by noneUsername
QwQ-32B-abliterated-AWQ-INT4 26 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
RoadToNowhere/Qwen3-32B-abliterated-Q4_K_M-GGUF 11K veeceey/Huihui-Qwen3-32B-abliterated-mlx-4bit 72 Yjuq/Qwen3-32B-abliterated-Q8_0-GGUF 43 hug-DJbfrj0555/Qwen3-32B-abliterated-Q3_K_S-GGUF 30
Total size
18.0 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-06-22 13:51
Source huggingface.co/noneUsername/Qwen3-32B-abliterated-awq ↗ Base model huihui-ai/Qwen3-32B-abliterated →

Files by quantization

Auxiliary files 16 files 18.0 GB
model-00002-of-00004.safetensors 4.66 GB 448d485b download
model-00001-of-00004.safetensors 4.63 GB db21b3bf download
model-00003-of-00004.safetensors 4.61 GB ba815a42 download
model-00004-of-00004.safetensors 4.11 GB a4cfb593 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 129 KB 53e20d4e download
tokenizer_config.json 5.28 KB ddaf6980 download
chat_template.jinja 4.02 KB 699ff8df download
README.md 3.15 KB 9bc475f8 download
.gitattributes 1.53 KB 52373fe2 download
config.json 909 B 2509a381 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 160 B bf86b0a4 download

README current version from Hugging Face

base_model:

  • huihui-ai/Qwen3-32B-abliterated

vllm (pretrained=/root/autodl-tmp/Qwen3-32B-abliterated,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,tensor_parallel_size=4,gpu_memory_utilization=0.8), 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 ↑ 0.900 ± 0.0190
strict-match 5 exact_match ↑ 0.896 ± 0.0193

vllm (pretrained=/root/autodl-tmp/Qwen3-32B-abliterated,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,tensor_parallel_size=4,gpu_memory_utilization=0.8), 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 ↑ 0.852 ± 0.0159
strict-match 5 exact_match ↑ 0.840 ± 0.0164
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7988 ± 0.0131
- humanities 2 none acc ↑ 0.7897 ± 0.0269
- other 2 none acc ↑ 0.7590 ± 0.0298
- social sciences 2 none acc ↑ 0.8722 ± 0.0252
- stem 2 none acc ↑ 0.7860 ± 0.0230

vllm (pretrained=/root/autodl-tmp/Qwen3-32B-abliterated-awq,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,tensor_parallel_size=2), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 1

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.892 ± 0.0197
strict-match 5 exact_match ↑ 0.888 ± 0.0200

vllm (pretrained=/root/autodl-tmp/Qwen3-32B-abliterated-awq,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), 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 ↑ 0.864 ± 0.0153
strict-match 5 exact_match ↑ 0.862 ± 0.0154
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7871 ± 0.0131
- humanities 2 none acc ↑ 0.8000 ± 0.0266
- other 2 none acc ↑ 0.7692 ± 0.0280
- social sciences 2 none acc ↑ 0.8611 ± 0.0260
- stem 2 none acc ↑ 0.7439 ± 0.0240

README history 1 version

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

  1. 2025-06-22Create README.md977dfb13.1 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