amd
/

gpt-oss-20b-w-mxfp4-a-bf16

8-bit precision

Model card Files Files and versions

⚠️ Important Notice

This model is intended solely for vLLM CI testing purposes and should not be used for any other purpose.

License

Modifications Copyright(c) 2025 Advanced Micro Devices, Inc. All rights reserved.

Downloads last month: 453

Safetensors

Model size

12B params

Tensor type

BF16

·

U8

·

Inference Providers NEW

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

Model tree for amd/gpt-oss-20b-w-mxfp4-a-bf16

Base model

openai/gpt-oss-20b

Quantized

(178)

this model