google/gemma-4-12B-it @ 12ace6d648d72bd41519e140f1185f34d38c7e3d quantized pack, published as majentik/gemma-4-12B-it-TurboQuant-MLX-4bit.

MLX quantization via mlx-vlm 0.6.3 (4bit, group_size 64); vision + audio towers retained in BF16 (not quantized).

Released under the TurboQuant line. RotorQuant and TurboQuant are this project's release labels for this pack, not distinct quantization algorithms — both brand repos for a given tier carry byte-identical weights, produced once and published under two names. No brand-specific speedup is claimed or measured for either label.

This pack is image-text-to-text capable: the vision and audio towers ship in BF16 alongside the quantized text tower, so image (and audio) inputs are supported end to end via mlx-vlm.

Vision fidelity note: for this instruct variant, vision has only been validated at 6-bit and 8-bit. Vision fidelity degrades below 6-bit; use 6-bit or 8-bit for image tasks.

Governed by the Gemma Terms of Use. See the upstream repo for the full license text.