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].

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

Part of Claude Code Local

Built by Matt Macosko in Arcata, CA. Open to work on local-AI and Apple Silicon inference: [email protected].