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

mlx-community/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-4bit-msq

mlx-community Gemma 1.7B
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/mlx-community%2FHuihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-4bit-msq"
Response includes
  • classification m1
  • files 13
  • hub_downloads_all_time 664
  • author_summary 207 models
  • readme_text full
Try next
GET/models?author=mlx-community
All 207 models by mlx-community
 GET/models?family=gemma&method=m1
Sibling gemma models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
664
120 last 30d - stable
Likes
4
Model age
3mo ago
created 2026-06-21
Downloads over time
Now706→from155↑355%
127339550761155 on Jun 24706 on Oct 11JunJulAugSepOct
Jun 24 → Oct 11 · 55 snapshots · spans 109 days

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.

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1 this lineage
mlx-community/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-4bit-msq↓ 120

Metadata

License
apache-2.0
Tags
transformers safetensors gemma4_unified image-text-to-text abliterated uncensored gemma4 coding code reasoning thinking text-generation

Related

Other by mlx-community
Qwen3.8-27B-Uncensored-OptiQ-4bit 16K Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit 7K Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp 5K Josiefied-Qwen3-4B-abliterated-v1-4bit 4K Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit 4K
Same base model
tpls/gemma-4-12B-coder-fable5-composer2.5-v1-abliterated 641 huihui-ai/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated 543 kang-heewon/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-oQ4-MLX 16 MyRayy/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated 14 KKKKKK1508777/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated 11
Total size
6.96 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-21 08:51
Source huggingface.co/mlx-community/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-4bit-msq ↗ Base model yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1 ↗

Files by quantization

Auxiliary files 13 files 6.99 GB
model-00001-of-00002.safetensors 4.99 GB aed74f5f download
model-00002-of-00002.safetensors 1.96 GB d494155e download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 132 KB 0109eaa9 download
config.json 22.4 KB c441e8eb download
chat_template.jinja 17.1 KB e61bbfe9 download
tokenizer_config.json 2.68 KB 81a6df7b download
.gitattributes 1.53 KB 52373fe2 download
README.md 945 B aff71eb1 download
processor_config.json 868 B 61c53634 download
quant_recipe.json 466 B b3575fe1 download
generation_config.json 273 B e41ee7af download
.gitignore 18.0 B 62687331 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
base_model:

  • yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1
    tags:
  • abliterated
  • uncensored
  • gemma4
  • coding
  • code
  • reasoning
  • thinking
  • safetensors
  • transformers

Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated — MLX 4.4 BPW

Mixed-precision MLX quantization of huihui-ai/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.

Details

  • Type: Vision (VLM)
  • Average: 4.45 bits per weight
  • Method: MLX Smart Quantize (MSQ)
  • AWQ scaling: applied to 96 groups

README history 1 version

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

  1. 2026-06-21Add files using upload-large-folder tool2f8b5cf945 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