Models /gpt-oss-120b /Can I run it?

Compatibility check

Can I run gpt-oss-120b on Radeon RX 9070?

No — it won't fit.

Too large

Too large

Too large

What is quantisation? →

Plan B — rent it

gpt-oss-120b is hosted by 21 providers from $0.36 per 1M output tokens (Google Vertex AI).Compare providers →

120B / 5.1B · full specs & benchmarks →

16 GB · everything it runs →