daslab-testing
/

Qwen3-8B-mxfp-w4-a4-GPTQ-hadamard-transform

8-bit precision

Model card Files Files and versions

No model card

Downloads last month: 62

Safetensors

Model size

4.94B params

Tensor type

F32

·

BF16

·

U8

·

Inference Providers NEW

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

Collection including daslab-testing/Qwen3-8B-mxfp-w4-a4-GPTQ-hadamard-transform

FP-Quant

FP-quantized models • 47 items • Updated 9 days ago • 2