haoyang-amd
/

output_oss_20b_moe_w_mxfp4_a_bfloat16

8-bit precision

Model card Files Files and versions

No model card

Downloads last month: 127

Safetensors

Model size

11B params

Tensor type

BF16

·

U8

·

Inference Providers NEW

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