Run gpt-oss-20b on an H100 80GB

15 GiB needed. 80 GiB on the card. It fits.

Deploy picks the cheapest GPU that fits. Flat 5% fee, shown before you start.

Versions that fit

OpenAI's open-weight 20B reasoning model.

VersionNeeds
llama.cpp · MXFP415 GiBDeploy
vLLM · MXFP422 GiBDeploy

Other GPUs for gpt-oss-20b

Questions

Does gpt-oss-20b fit on an H100 80GB?
Yes. It needs 15 GiB of VRAM and the H100 80GB has 80 GiB.
What does it cost to run gpt-oss-20b on an H100 80GB?
Hosts set the hourly price. You see it, with our flat 5% fee inside, before anything starts. See live H100 80GB offers.
How do I use gpt-oss-20b once it runs?
It serves an OpenAI-compatible API. The rental page gives you the URL and a key.