Gemma 4 12B It TurboQuant MLX 3bit

--- base_model: google/gemma-4-12B-it license: gemma library_name: mlx pipeline_tag: image-text-to-text tags: - mlx - quantized - gemma - gemma4 - image-text-to-text - apple-silicon - turboquant --- # gemma-4-12B-it — TurboQuant MLX 3bit [`google/gemma-4-12B-it`](https://huggingface.co/google/gemma-4-12B-it) @ `12ace6d648d72bd41519e140f1185f34d38c7e3d` quantized pack, published as `majentik/gemma-4-12B-it-TurboQuant-MLX-3bit`. ## Method MLX quantization via mlx-vlm 0.6.3 (3bit, group_size 64); vision + audio towers retained in BF16 (not quantized). ## Release line 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. ## Modality 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. ## License Governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). See the upstream repo for the full license text.

Source context: 34 downloads · 0 likes · Pipeline image-text-to-text · Library mlx · Repo majentik/gemma-4-12B-it-TurboQuant-MLX-3bit

Source context: 81 downloads · 0 likes · Pipeline image-text-to-text · Library mlx · Repo majentik/gemma-4-12B-it-TurboQuant-MLX-3bit