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

ngxson/LoRA-QwQ-32B-Preview-abliterated

ngxson Qwen 32B
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/ngxson%2FLoRA-QwQ-32B-Preview-abliterated"
Response includes
  • classification m5
  • files 4
  • benchmarks 10 entries
  • author_summary 11 models
  • readme_text full
Try next
GET/models?author=ngxson
All 11 models by ngxson
 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 · 30-day
0
Likes
0
Model age
21mo ago
created 2025-01-09
Downloads over time
Now0→from0↑0%
00110 on Jan 8, 20250 on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 8, 2025 → Oct 11 · 131 snapshots · spans 641 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 3410 LM-Arena
LM Arena Elo 1170.8455163227195 LM-Arena
Arena-Elo-Lower 1159.8739878857011 LM-Arena
Arena-Elo-Upper 1181.8170447597379 LM-Arena
Arena-Rank 156 LM-Arena
BBH average 0.581787521079258 OpenLLM-v2
IFEval instruct 0.46882494004796166 OpenLLM-v2
IFEval-Prompt 0.33826247689463956 OpenLLM-v2
MATH lvl 5 0.22885196374622357 OpenLLM-v2
MMLU-Pro 0.5678191489361702 OpenLLM-v2

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-Preview this lineage
ngxson/LoRA-QwQ-32B-Preview-abliterated

Metadata

Tags
transformers safetensors mergekit peft base_model:Qwen/QwQ-32B-Preview base_model:finetune:Qwen/QwQ-32B-Preview endpoints_compatible region:us

Related

Other by ngxson
DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF 851 Llama-3-Instruct-abliteration-LoRA-8B-F16-GGUF 138 LoRA-Qwen2.5-7B-Instruct-abliterated-v3 0 LoRA-Qwen2.5-14B-Instruct-abliterated-v2 0 LoRA-phi-4-abliterated 0
Same base model
huihui-ai/QwQ-32B-Preview-abliterated 71 pipihand01/QwQ-32B-Preview-abliterated-linear75 22 pipihand01/QwQ-32B-Preview-abliterated-linear25 15 async0x42/QwQ-32B-Preview-abliterated-exl2_4.65bpw 12 pipihand01/QwQ-32B-Preview-abliterated-linear50 11
Total size
533 MB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-01-09 22:02
Source huggingface.co/ngxson/LoRA-QwQ-32B-Preview-abliterated ↗ Base model Qwen/QwQ-32B-Preview ↗

Files by quantization

Auxiliary files 4 files 533 MB
adapter_model.safetensors 533 MB 16207583 download
.gitattributes 1.48 KB a6344aac download
adapter_config.json 772 B 38e8c14e download
README.md 734 B 02bd4ae5 download

README current version from Hugging Face

base_model:

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

Untitled LoRA Model (1)

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-Preview-abliterated and uses Qwen/QwQ-32B-Preview as a base.

Parameters

The following command was used to extract this LoRA adapter:

mergekit-extract-lora huihui-ai/QwQ-32B-Preview-abliterated Qwen/QwQ-32B-Preview OUTPUT_PATH --rank=32 --device=cuda

README history 1 version

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

  1. 2025-01-09Upload folder using huggingface_hubbd5f7a8734 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