Run gpt-oss-20b on an L4
15 GiB needed. 24 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.
Other GPUs for gpt-oss-20b
Questions
Does gpt-oss-20b fit on an L4?
Yes. It needs 15 GiB of VRAM and the L4 has 24 GiB.
What does it cost to run gpt-oss-20b on an L4?
Hosts set the hourly price. You see it, with our flat 5% fee inside, before anything starts. See live L4 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.