baa-ai
/

Qwen3.5-122B-A10B-RAM-100GB-MLX

mixed-precision

Mixture of Experts

4-bit precision

Model card Files Files and versions

Qwen3.5-122B-A10B-RAM-100GB-MLX / model-00008-of-00019.safetensors

Commit History

Reconvert with mlx_vlm: restore vision encoder weights

d4105c2
verified

tomkay commited on Apr 7

RAM 100GB mixed-precision quantization of Qwen3.5-122B-A10B

c3f1a71
verified

tomkay commited on Apr 7