daslab-testing
/

Qwen3-32B-mxfp-w4-a4-MicroQAT-hadamard-transform

8-bit precision

Model card Files Files and versions

No model card

Downloads last month: 23

Safetensors

Model size

18.1B params

Tensor type

F32

·

BF16

·

U8

·

Inference Providers NEW

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