OpenAI · 21B (3.6B active) parameters · Apache 2.0
What GPU do you need to run gpt-oss-20b?Memory, cards and speed.
gpt-oss-20b needs about 14 GB of GPU memory (VRAM) at its smallest (MXFP4, as published), so a 16 GB card such as an RTX 4080 runs it. The cheapest card on our list that fits, an RTX 4060 Ti 16GB, costs about $0.14 an hour.
GPU memory
gpt-oss-20b, by version.
Includes about 1.5 GB for the program and a short conversation (about 4,000 tokens). Long conversations need more. Speeds are ceilings: real speeds are usually half to two-thirds of them. How we work it out
| Version | Memory needed | Card size | Cards that fit | From | Top speed |
|---|---|---|---|---|---|
| MXFP4, as published | about 14 GB | 16–20 GB | RTX 4090, RTX 5090, RTX 3090, RTX 4080, RTX 3090 Ti, RTX 5080, RTX 5070 Ti, RTX 4070 Ti SUPER, RTX 5060 Ti 16GB, RTX 4060 Ti 16GB | $0.14/hr on an RTX 4060 Ti 16GB | Faster than its size suggests |
OpenAI's smaller open-weight model, published already compressed. OpenAI says it runs within 16 GB of memory.
Run it
Start gpt-oss-20b in minutes.
On KernelMachine, Rent a Chat model with it: it loads into the chat app by itself once the rental is ready, straight from Ollama to the machine, and is in the app's model menu. On any machine with Ollama, one command downloads and runs it. Ollama on a rented GPU
$ ollama run gpt-oss:20b
# Model files: huggingface.co/openai/gpt-oss-20b
Common questions
Questions, answered plainly.
How much VRAM does gpt-oss-20b need?
MXFP4, as published: about 14 GB. That includes about 1.5 GB for the program and a short conversation; longer conversations need more.
Can an RTX 4090 run gpt-oss-20b?
Yes. gpt-oss-20b (MXFP4, as published) needs about 14 GB, which fits in the RTX 4090's 24 GB.
How fast does gpt-oss-20b run?
Faster than its size suggests. It's a mixture-of-experts model, so it reads only about 3.6B of its 21B parameters for each word.
Can I run gpt-oss-20b on KernelMachine?
Yes. Rent a Chat model with gpt-oss-20b, on this page, starts the chat app on the cheapest card with 16 GB or more, and gpt-oss:20b loads into it by itself once it's ready. Already renting a Chat model? Pick gpt-oss-20b on the rental's page, or download gpt-oss:20b from the chat app's model menu.
Other models
Compare with other chat models.
Preparing an invite-only beta
Get an email when access opens.
No launch date is set. We'll email you once when KernelMachine opens. Nothing else.