base_model: OpenYourMind/gemma-4-12B-it-abliterated-uncensored
base_model_relation: quantized
license: gemma
language:
- en
library_name: mlx
pipeline_tag: text-generation
tags: - mlx
- gemma
- gemma-4
- abliterated
- apple-silicon
- mlx-lm
- local-llm
- on-device
- macbook
- uncensored
- 12b
- 4-bit
gemma-4-12B-it-abliterated-4bit-mlx
Uncensored Gemma 4 12B on Apple Silicon — the light one. Abliterated, 4-bit MLX, 11 GB and happy on a 24 GB Mac. No cloud, no API key, no refusals.
A 4-bit MLX build of an abliterated Gemma 4 12B, packaged for Apple Silicon. This is the lightweight tier of the divinetribe roster — it runs comfortably on a 32 GB Mac where the 31B is tight.
- Base model: OpenYourMind/gemma-4-12B-it-abliterated-uncensored
- Quantization: 4-bit, group size 64 (MLX)
- Architecture: Gemma 4 (unified) — converted with mlx-vlm
Use with MLX
pip install mlx-vlm
python -m mlx_vlm.generate --model divinetribe/gemma-4-12B-it-abliterated-4bit-mlx --prompt "Hello" --max-tokens 256
Drop-in for the claude-code-local stack — point MLX_MODEL at this repo.
Note
"Abliterated" suppresses the model's built-in refusal direction so it won't refuse benign-but-edgy requests. It is not a capability upgrade, and you remain bound by the upstream Gemma license. Use it responsibly.
Abliteration by OpenYourMind. MLX conversion + quantization by divinetribe.
More abliterated MLX models
Part of the Abliterated MLX for Apple Silicon
collection — 11 uncensored models converted for Macs, from Gemma 4 12B up to
Llama 3.3 70B, plus Qwen3, Qwen3-VL, Hermes 4 and Muse Glimmer 30B.
Part of Claude Code Local
This model is one of the fighters in Claude Code Local (3.2k★), which runs Claude Code 100% on-device on Apple Silicon through an MLX-native Anthropic-API server. Not sure which local model to run as an agent? Check the Agent-12 local agent leaderboard: real agent tasks, judged by the filesystem, same hardware for every row.
Built by Matt Macosko in Arcata, CA. Open to work on local-AI and Apple Silicon inference: [email protected].