base_model:
- Qwen/Qwen3-32B
Model abliterated using techniques from blogs:
https://huggingface.co/blog/grimjim/projected-abliteration
https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration
vprilepskii/Qwen3-32B-biprojected-norm-preserving-abliterated
Your rig
guess connected
? Why do I need an app?
The browser can't see your hardware
For privacy reasons a browser tells us at most "≥ 8 GB RAM, 8 cores" - same reading whether you have 8 GB or 128 GB. It has no idea how much RAM is free right now, which apps are open, or whether you have a GPU.
The Abliteration app is integrated with your machine
It reads your exact RAM, GPU model and VRAM, free memory right now, and picks the sharpest quant that still fits. Every model page lights up precisely for your rig.
And you can chat with any model, right now
The app is a full local runtime - no API keys, no subscription, everything runs on your machine. Click any model on this site and start a conversation in seconds.
Get the free 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/vprilepskii%2FQwen3-32B-biprojected-norm-preserving-abliterated" Response includes
- classification m1
- files 26
- benchmarks 16 entries
- hub_downloads_all_time 54
- author_summary 4 models
- readme_text full
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)
Refusal direction extracted via
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
54
18 last 30d
- stable
Likes
0
Descendants
1
in 1 direct fork
Model age
10mo ago
created 2025-11-25
Downloads over time
Nov 26, 2025 → Oct 12 · 86 snapshots · spans 320 days
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| Entertainment | 1.6 | UGI |
| Hazardous | 2.9 | UGI |
| Natural Intelligence | 20.46 | UGI |
| Political lean | -11.2% | UGI |
| Sensitive-Info | 18.93 | UGI |
| SocPol | 1.4 | UGI |
| UGI | 37.62 | UGI |
| Willingness (10) | 7.5 | UGI |
| W10-Adherence | 7 | UGI |
| W10-Direct | 8 | UGI |
| Writing | 31.82 | UGI |
Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
| Benchmark | Score | Source |
|---|---|---|
| Arena-Battles | 4074 | LM-Arena |
| LM Arena Elo | 1342.167437107052 | LM-Arena |
| Arena-Elo-Lower | 1332.961474599781 | LM-Arena |
| Arena-Elo-Upper | 1351.3733996143228 | LM-Arena |
| Arena-Rank | 45 | LM-Arena |
Genealogy
Full fork graph →This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.
Metadata
Related
Source huggingface.co/vprilepskii/Qwen3-32B-biprojected-norm-preserving-abliterated ↗ Base model Qwen/Qwen3-32B ↗
Files by quantization
Auxiliary files 26 files 61.0 GB
| model-00001-of-00014.safetensors | 4.59 GB | e5da875a | download |
| model-00004-of-00014.safetensors | 4.54 GB | 9459bdad | download |
| model-00005-of-00014.safetensors | 4.54 GB | 75970b7a | download |
| model-00006-of-00014.safetensors | 4.54 GB | b094f494 | download |
| model-00007-of-00014.safetensors | 4.54 GB | 3408a0ed | download |
| model-00008-of-00014.safetensors | 4.54 GB | a2387fc3 | download |
| model-00009-of-00014.safetensors | 4.54 GB | f08a3a38 | download |
| model-00010-of-00014.safetensors | 4.54 GB | f3a31a07 | download |
| model-00011-of-00014.safetensors | 4.54 GB | f4e2695e | download |
| model-00012-of-00014.safetensors | 4.54 GB | 42fb9b2b | download |
| model-00013-of-00014.safetensors | 4.54 GB | 00bd4f8f | download |
| model-00003-of-00014.safetensors | 4.54 GB | fbbc2973 | download |
| model-00002-of-00014.safetensors | 4.54 GB | 007c079c | download |
| model-00014-of-00014.safetensors | 1.94 GB | 2e6ace17 | 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 | 57.0 KB | 9c12a5bc | download |
| tokenizer_config.json | 5.28 KB | ddaf6980 | download |
| chat_template.jinja | 4.07 KB | 01be9b30 | download |
| config.json | 2.10 KB | 58804ef2 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| added_tokens.json | 707 B | b54f9135 | download |
| special_tokens_map.json | 613 B | ac23c0aa | download |
| README.md | 222 B | b07811d5 | download |
| generation_config.json | 214 B | 9e289a1a | download |
README
README history
The author's README evolved over time. Click a version to see its content at that point.
2025-11-25Create README.md
Loading...