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

huizimao/gpt-oss-120b-uncensored-mxfp4

huizimao Gpt-oss 118B
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/huizimao%2Fgpt-oss-120b-uncensored-mxfp4"
Response includes
  • classification m-uncensored
  • files 22
  • benchmarks 16 entries
  • hub_downloads_all_time 3,302
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=huizimao
All 4 models by huizimao
 GET/models?family=gpt-oss&method=m-uncensored
Sibling gpt-oss models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
3K
188 last 30d - cooling
Likes
7
Model age
14mo ago
created 2025-08-11
Downloads over time
Now3.4K→from40↑8,370%
01.2K2.5K3.7K40 on Aug 13, 20253.4K on Oct 11Aug '25Oct '25Dec '25FebAprJunAugOct
Aug 13, 2025 → Oct 11 · 100 snapshots · spans 424 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 8335 LM-Arena
LM Arena Elo 1365.960115714145 LM-Arena
Arena-Elo-Lower 1359.0774821030143 LM-Arena
Arena-Elo-Upper 1372.842749325276 LM-Arena
Arena-Rank 28 LM-Arena
Entertainment 1.8 UGI
Hazardous 3.5 UGI
Natural Intelligence 33.68 UGI
Political lean -15.3% UGI
Sensitive-Info 19.48 UGI
SocPol 0.8 UGI
UGI 19.65 UGI
Willingness (10) 2 UGI
W10-Adherence 3 UGI
W10-Direct 1 UGI
Writing 38.52 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.

openai/gpt-oss-120b this lineage
huizimao/gpt-oss-120b-uncensored-mxfp4↓ 188

Variants by this author 2 formats · 348 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
safetensors gpt_oss base_model:openai/gpt-oss-120b base_model:quantized:openai/gpt-oss-120b license:apache-2.0 8-bit mxfp4 region:us

Related

Other by huizimao
gpt-oss-120b-uncensored-bf16 160 gpt-oss-20b-uncensored-bf16 159 gpt-oss-20b-uncensored-mxfp4 62
Same base model
HauhauCS/GPTOSS-120B-Uncensored-HauhauCS-Aggressive 23K wangzhang/gpt-oss-120b-abliterated 284 Unrestricted/GPTOSS-120B-Uncensored-HauhauCS-Aggressive 269 huizimao/gpt-oss-120b-uncensored-bf16 160 joshebbs/gpt-oss-120b-abliterated 144
Total size
60.8 GB
Files
22
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-08-11 04:05
Source huggingface.co/huizimao/gpt-oss-120b-uncensored-mxfp4 ↗ Base model openai/gpt-oss-120b ↗

Files by quantization

Auxiliary files 22 files 60.8 GB
model-00001-of-00015.safetensors 4.38 GB 6fb61138 download
model-00006-of-00015.safetensors 4.31 GB 90bbf16b download
model-00008-of-00015.safetensors 4.31 GB 15222c03 download
model-00010-of-00015.safetensors 4.31 GB 30b13ca0 download
model-00012-of-00015.safetensors 4.31 GB f5556520 download
model-00014-of-00015.safetensors 4.31 GB 80f68e18 download
model-00002-of-00015.safetensors 4.31 GB 70ca048e download
model-00004-of-00015.safetensors 4.31 GB 9ab932cf download
model-00005-of-00015.safetensors 3.83 GB 1c824a03 download
model-00007-of-00015.safetensors 3.83 GB 62c68717 download
model-00009-of-00015.safetensors 3.83 GB 9db80a59 download
model-00011-of-00015.safetensors 3.83 GB bfcbcb34 download
model-00013-of-00015.safetensors 3.83 GB 21c205ea download
model-00003-of-00015.safetensors 3.83 GB 0b62f20e download
model-00015-of-00015.safetensors 3.23 GB b431b0cc download
tokenizer.json 26.6 MB 0614fe83 download
model.safetensors.index.json 56.0 KB 54eb081c download
tokenizer_config.json 4.10 KB c021cddb download
config.json 2.04 KB 42300b89 download
.gitattributes 1.53 KB 52373fe2 download
README.md 814 B a0750f7a download
generation_config.json 160 B 729cb147 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • openai/gpt-oss-120b

This is the MXFP4 PTQ version of huizimao/gpt-oss-120b-uncensored-bf16.

Finetuning is done on Amazon FalseReject train set with 800 samples.

PTQ is done with NVIDIA ModelOpt

Evaluation results obtained on Amazon FalseReject test set with 300 samples.

Model Variants False refusal rate
gpt-oss-120b original (MXFP4) 70%
LoRA (BF16) 6%
LoRA + PTQ (MXFP4) - this model 24%

Code example, documentation, and further QAT checkpoints will be released soon.

README history 1 version

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

  1. 2025-08-11Create README.md0b5936b814 B
    Loading...

Discussions 1 thread

  1. 2025-08-20Very bad uncensoredopen2 💬#1
    Loading...

Continue on Hugging Face →

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