georgeis55/Muse-Glimmer-30B-MLX-6bit
098
georgeis55/Muse-Glimmer-30B-MLX-6bit
MLX conversion of meta-models/Muse-Glimmer-30B at 6-bit, made on an M1 Ultra.
Not supported by any released mlx-vlm, so it won't load in LM Studio. Works in oMLX today. For mlx-vlm, install the open PR:
pip install "mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git@refs/pull/1839/head"Built from #1839 (quantized embedding keeps embed_norm), on top of the port in #1838. Thanks to @Blaizzy and @johntdavies.
