Models /gpt-oss-safeguard-20b /Can I run it?
Compatibility check

Can I run gpt-oss-safeguard-20b on Apple M1 (8-core GPU)?

Partially — with CPU offload.best quant:

13.6 GB of weights, plus 1.7 GB for the software that runs it and the smallest conversation it can hold, comes to 15.3 GB against the 12 GB this 16 GB device leaves free.

Decode speed
—
Usable context
—
Memory
16 GB
Spills to system RAM
Spills to system RAMest
Too large
What is quantisation? →
Plan B — rent it

gpt-oss-safeguard-20b is hosted by 12 providers from $0.15 per 1M output tokens (Amazon Bedrock).Compare providers →

gpt-oss-safeguard-20b
21.5B / 3.6B · full specs & benchmarks →
Apple M1 (8-core GPU)
16 GB · everything it runs →