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

TheCluster/gemma-3-27b-it-uncensored-mlx-6bit

TheCluster Gemma 27B multimodal
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/TheCluster%2Fgemma-3-27b-it-uncensored-mlx-6bit"
Response includes
  • classification m-uncensored
  • files 18
  • benchmarks 16 entries
  • hub_downloads_all_time 1,633
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=TheCluster
All 28 models by TheCluster
 GET/models?family=gemma&method=m-uncensored
Sibling gemma 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
2K
35 last 30d - cooling
Likes
1
Model age
18mo ago
created 2025-03-28
Downloads over time
Now1.6K→from15↑10,853%
06021.2K1.8K15 on Mar 26, 20251.6K on Oct 111.6K on Oct 9Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 26, 2025 → Oct 11 · 120 snapshots · spans 564 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 37211 LM-Arena
LM Arena Elo 1358.3955692803715 LM-Arena
Arena-Elo-Lower 1354.342781362301 LM-Arena
Arena-Elo-Upper 1362.4483571984422 LM-Arena
Arena-Rank 37 LM-Arena
Entertainment 1.1 UGI
Hazardous 2.4 UGI
Natural Intelligence 34.45 UGI
Political lean -14.2% UGI
Sensitive-Info 20.64 UGI
SocPol 3 UGI
UGI 20.43 UGI
Willingness (10) 2 UGI
W10-Adherence 0 UGI
W10-Direct 4 UGI
Writing 44.99 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.

google/gemma-3-27b-it this lineage
TheCluster/gemma-3-27b-it-uncensored-mlx-6bit↓ 35

Metadata

License
gemma
Languages
en fr es de it hi ru
Tags
mlx safetensors gemma3 chat uncensored apple 6bit image-text-to-text conversational en fr es

Related

Other by TheCluster
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8 7K Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-mxfp4 7K Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MLX-mxfp4 1K Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8 1K Qwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-MLX-mixed-9.4bit 916
Same base model
mlabonne/gemma-3-27b-it-abliterated-GGUF 8K mlabonne/gemma-3-27b-it-abliterated 7K Thaurock/Gemma-3-27b-it-abliterated-GGUF 877 llmfan46/gemma-3-27b-it-ultra-uncensored-heretic-GGUF 531 TheCluster/gemma-3-27b-it-uncensored-mlx-4bit 435
Total size
22.3 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-16 15:27
Source huggingface.co/TheCluster/gemma-3-27b-it-uncensored-mlx-6bit ↗ Base model google/gemma-3-27b-it ↗

Files by quantization

Auxiliary files 18 files 22.3 GB
model-00002-of-00005.safetensors 5.00 GB 69821092 download
model-00004-of-00005.safetensors 5.00 GB d527aa89 download
model-00003-of-00005.safetensors 5.00 GB 756d3056 download
model-00001-of-00005.safetensors 4.99 GB b49a6b51 download
model-00005-of-00005.safetensors 2.30 GB 69262ecb download
tokenizer.json 31.8 MB 4667f208 download
tokenizer.model 4.47 MB 1299c11d download
tokenizer_config.json 1.10 MB 434d438a download
model.safetensors.index.json 124 KB 481bf923 download
config.json 1.93 KB 1e6b77b6 download
chat_template.json 1.58 KB 719b0cd0 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.28 KB 79602a80 download
special_tokens_map.json 720 B b7a8e475 download
preprocessor_config.json 570 B b1e00fc1 download
generation_config.json 192 B f60a6730 download
processor_config.json 70.0 B 453c7966 download
added_tokens.json 35.0 B e17bde03 download

README current version from Hugging Face

license: gemma
base_model:

  • google/gemma-3-27b-it
  • nidum/Nidum-gemma-3-27B-it-Uncensored
    base_model_relation: quantized
    pipeline_tag: image-text-to-text
    tags:
  • chat
  • mlx
  • uncensored
  • gemma3
  • apple
  • 6bit
    language:
    • en
    • fr
    • es
    • de
    • it
    • hi
    • ru
      library_name: mlx

Gemma-3-27B Instruct Uncensored 6-bit MLX

Uncensored version of Gemma 3 27B.

Also you can try new uncensored version: Amoral Gemma-3 27B 6-bit MLX

Technical Details

Supports a context length of 128k tokens, with a max output of 8192.

Multimodal supporting images normalized to 896 x 896 resolution.

Refer to the original model card and uncensored model for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model TheCluster/gemma-3-27b-it-uncensored-mlx-6bit --max-tokens 256 --temperature 0.4 --prompt "Describe this image." --image <path_to_image>

Source

This model was converted to MLX format from nidum/Nidum-gemma-3-27B-it-Uncensored using mlx-vlm version 0.1.19.

README history 4 versions

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

  1. 2025-04-16Update README.mdecc23781.3 KB
    Loading...
  2. 2025-03-28Update README.mdde83fe9998 B
    Loading...
  3. 2025-03-28Create README.md8c28cb6994 B
    Loading...
  4. 2025-03-28initial commit934df2123 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