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

chenrm/qwq-32b-abliterated-lora

chenrm Qwen 32B GGUF
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/chenrm%2Fqwq-32b-abliterated-lora"
Response includes
  • classification m5
  • files 3
  • benchmarks 21 entries
  • hub_downloads_all_time 199
  • author_summary 9 models
  • readme_text full
Try next
GET/models?author=chenrm
All 9 models by chenrm
 GET/models?family=qwen&method=m5
Sibling qwen models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
199
16 last 30d - cooling
Likes
2
Model age
19mo ago
created 2025-03-17
Downloads over time
Now207→from16↑1,194%
68015322616 on Mar 12, 2025207 on Oct 11207 on Oct 10Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 12, 2025 → Oct 11 · 122 snapshots · spans 578 days

Benchmarks

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 24359 LM-Arena
LM Arena Elo 1333.1043906834145 LM-Arena
Arena-Elo-Lower 1328.5976095286157 LM-Arena
Arena-Elo-Upper 1337.6111718382135 LM-Arena
Arena-Rank 50 LM-Arena
BBH average 0.3017252561940589 OpenLLM-v2
IFEval instruct 0.47002398081534774 OpenLLM-v2
IFEval-Prompt 0.32532347504621073 OpenLLM-v2
MATH lvl 5 0.1608761329305136 OpenLLM-v2
MMLU-Pro 0.11959773936170212 OpenLLM-v2
Entertainment 1.4 UGI
Hazardous 4.1 UGI
Natural Intelligence 24.06 UGI
Political lean -18.6% UGI
Sensitive-Info 27.21 UGI
SocPol 3.2 UGI
UGI 27.3 UGI
Willingness (10) 2.8 UGI
W10-Adherence 2.5 UGI
W10-Direct 3 UGI
Writing 34.87 UGI

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.

Qwen/QwQ-32B this lineage
chenrm/qwq-32b-abliterated-lora↓ 16

Metadata

Tags
peft safetensors gguf mergekit base_model:Qwen/QwQ-32B base_model:adapter:Qwen/QwQ-32B region:us

Related

Other by chenrm
qwen3-vl-30b-a3b-instruct-abliterated-h-corpus 124 qwen3.8-flash-next-abliterated-lora 96 qwen2.5-vl-32b-abliterated-h-corpus 59 qwen2.5-14b-deepsex-abliterated-h-corpus 51 qwen3-30b-a3b-abliterated-lora 46
Same base model
huihui-ai/QwQ-32B-abliterated 148 async0x42/QwQ-32B-abliterated-exl3_4.5bpw 40 TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2 26 matatonic/QwQ-32B-abliterated-4.25bpw-exl2 21 thirdeyeai/QwQ-32B-uncensored 21
Total size
1.00 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-17 07:50
Source huggingface.co/chenrm/qwq-32b-abliterated-lora ↗ Base model Qwen/QwQ-32B ↗

Files by quantization

Auxiliary files 3 files 1.00 GB
qwq-32b-abliterated-lora.gguf 1.00 GB aeb3dc9f download
.gitattributes 1.55 KB 7bd29e4e download
README.md 720 B 7cc4f005 download

README current version from Hugging Face

base_model:

  • Qwen/QwQ-32B
  • huihui-ai/QwQ-32B-abliterated
    library_name: peft
    tags:
  • mergekit
  • peft

qwq-32b-abliterated-lora

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from huihui-ai/QwQ-32B-abliterated and uses Qwen/QwQ-32B as a base.

Parameters

The following command was used to extract this LoRA adapter:

/venv/main/bin/mergekit-extract-lora --model huihui-ai/QwQ-32B-abliterated --base-model Qwen/QwQ-32B --out-path qwq-32b-abliterated-lora --cuda --max-rank 32

README history 1 version

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

  1. 2025-03-17Upload folder using huggingface_hubf772256720 B
    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