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 / config.json

Commit History

Reconvert with mlx_vlm: restore vision encoder weights

946ef4c
verified

tomkay commited on Apr 7

RAM 25GB mixed-precision quantization of Qwen3.5-35B-A3B

f24fbce
verified

tomkay commited on Apr 5