Views
No views yet
pip install mlx-lm release. Other 12B MLX builds still stop with Model type gemma4_unified not supported on mlx-lm 0.31.3, the newest version on PyPI. This one is stripped to the text tower and relabeled gemma4, so it loads with no patching. 11 GB, 24 GB Mac.mlx_lm — the same way divinetribe/gemma-4-31b-it-abliterated-4bit-mlx does.google/gemma-4-12B-it with model_type: gemma4_unified (text + vision +
audio in one checkpoint), while the 31B ships as plain model_type: gemma4. mlx_lm
has a gemma4 loader but no gemma4_unified loader in the current PyPI release
(0.31.3, uploaded 2026-04-22), so every standard 12B MLX build (including the
4-bit/8-bit/bf16 mlx-community ones) fails there with:ValueError: Model type gemma4_unified not supported.Upstream status (checked 2026-08-12): this was fixed on mlx-lmmainin #1349 (merged 2026-06-05), which remapsgemma4_unifiedto thegemma4loader and strips the towers insanitize(). It has not shipped to PyPI yet, sopip install mlx-lmstill hits the error above. Once a release carries it, the standardmlx-communitybuilds will load too and this repo's advantage becomes just the abliteration.
mlx_vlm then hangs, because it tries to spin up vision and
audio towers a text-only server never feeds.vision_embedder,
embed_vision, embed_audio, …) and relabeling model_type: gemma4, leaving only the
language_model.* tensors. The 4-bit abliterated weights are preserved byte-for-byte —
nothing is re-quantized. The result loads in plain mlx_lm like any text model.pip install mlx-lm1from mlx_lm import load, generate
2model, tok = load("divinetribe/gemma-4-12B-it-abliterated-4bit-mlx-text")
3print(generate(model, tok, prompt="Hello", max_tokens=128))MLX_MODEL=divinetribe/gemma-4-12B-it-abliterated-4bit-mlx-textdivinetribe/gemma-4-12B-it-abliterated-4bit-mlx — same abliteration,
text tower only. Base: google/gemma-4-12B-it.