baa-ai
/

Qwen3.5-35B-A3B-RAM-25GB-MLX

mixed-precision

Mixture of Experts

4-bit precision

Model card Files Files and versions

Qwen3.5-35B-A3B-RAM-25GB-MLX / video_preprocessor_config.json

Commit History

Reconvert with mlx_vlm: restore vision encoder weights

946ef4c
verified

tomkay commited on Apr 7