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

HauhauCS/GPT-OSS-20B-Uncensored-HauhauCS-Balanced

HauhauCS Gpt-oss 20B GGUF 131K ctx
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/HauhauCS%2FGPT-OSS-20B-Uncensored-HauhauCS-Balanced"
Response includes
  • classification m8
  • files 3
  • benchmarks 5 entries
  • hub_downloads_all_time 14,505
  • author_summary 26 models
  • readme_text full
Try next
GET/models?author=HauhauCS
All 26 models by HauhauCS
 GET/models?family=gpt-oss&method=m8
Sibling gpt-oss models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

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.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
15K
3K last 30d - stable
HF trending score
1
mild recent interest
Likes
20
Model age
8mo ago
created 2026-01-24
Downloads over time
Now15.2K→from0↑0%
05.6K11.2K16.7K0 on Jan 2115.2K on Oct 11JanMarMayJulSep
Jan 21 → Oct 11 · 85 snapshots · spans 263 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 7952 LM-Arena
LM Arena Elo 1307.3530229799078 LM-Arena
Arena-Elo-Lower 1300.2396666200118 LM-Arena
Arena-Elo-Upper 1314.4663793398038 LM-Arena
Arena-Rank 70 LM-Arena

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.

gpt-oss-20b this lineage
HauhauCS/GPT-OSS-20B-Uncensored-HauhauCS-Balanced↓ 2,609

Metadata

License
other
Languages
en
Tags
gguf uncensored abliterated mxfp4 en license:other endpoints_compatible region:us conversational

Related

Other by HauhauCS
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 2.1M Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 1.4M Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced 970K Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 854K Qwen3.5-9B-Uncensored-HauhauCS-Aggressive 715K
Same base model
HauhauCS/GPT-OSS-20B-Uncensored-HauhauCS-Aggressive 8K Unrestricted/GPT-OSS-20B-Uncensored-HauhauCS-Balanced 417 Unrestricted/GPT-OSS-20B-Uncensored-HauhauCS-Aggressive 201 nguyenthilaitrieulong/GPT-OSS-20B-Uncensored-HauhauCS-Aggressive 148 tripolskypetr/GPTOSS-Uncensored-Aggressive-GGUF 90
Total size
11.3 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-05 19:00
Source huggingface.co/HauhauCS/GPT-OSS-20B-Uncensored-HauhauCS-Balanced ↗ Base model gpt-oss-20b ↗

Files by quantization

Auxiliary files 3 files 11.3 GB
GPT-OSS-20B-Uncensored-HauhauCS-MXFP4-Balanced.gguf 11.3 GB 0a80af8f download
.gitattributes 1.57 KB 331d61b0 download
README.md 995 B d6719b16 download

README current version from Hugging Face

license: other
base_model: gpt-oss-20b
tags:

  • uncensored
  • abliterated
  • gguf
  • mxfp4
    language:
  • en

GPT-OSS-20B-Uncensored-HauhauCS-Balanced

Join the Discord for updates, roadmaps, projects, or just to chat.

Uncensored version of GPT-OSS 20B. This is the balanced variant - more conservative tuning that prioritizes keeping the model's general capabilities intact.

If you want fewer refusals and don't mind being a bit more experimental, check out the Aggressive variant.

Format

MXFP4 GGUF. Works with llama.cpp, ollama, LM Studio, and anything else that loads GGUFs.

LM Studio

Compatible with Reasoning Effort custom buttons. To use them, put the model in:

LM Models\lmstudio-community\gpt-oss-20b-GGUF\

About

  • Base model: GPT-OSS 20B
  • Abliterated with custom tooling
  • This is the safer pick if you're not sure which to grab

README history 4 versions

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

  1. 2026-04-05Upload README.md with huggingface_hub7a90978995 B
    Loading...
  2. 2026-01-24add lm studio info330ddf0888 B
    Loading...
  3. 2026-01-24add metadata6ffeb28738 B
    Loading...
  4. 2026-01-24add readmecc12954617 B
    Loading...

Discussions 1 thread

  1. 2026-04-05Discord serveropen2 💬#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