Modelpublic

mlx-community/gemma-4-12B-coder-fable5-composer2.5-v1-4bit-msq

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

7likes141downloads

Model Card

gemma-4-12B-coder-fable5-composer2.5-v1 — MLX 4.5 BPW

Mixed-precision MLX quantization of `yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1`, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.

Details

—Type: Vision (VLM)
—Average: 4.5 bits per weight
—Method: MLX Smart Quantize (MSQ)
—AWQ scaling: applied to 96 groups