amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 download history

amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 is an 11.4B-parameter model model by amd. In the last 30 days it was downloaded 4,588 times (1,063 in the last 7 days), and 59,417 times in total.

It ranks #12,205 on the Hub by monthly downloads.

It has 2 likes.

It is a quantization of openai/gpt-oss-20b.

Open amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 on Hugging Face