medmekk
/

Qwen3.5-35B-A3B-MXFP4

8-bit precision

Model card Files Files and versions

No model card

Downloads last month: 50

Safetensors

Model size

21B params

Tensor type

U8

·

BF16

·

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support