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

Can I run gpt-oss-120b on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:
Decode speed
158 tok/sest
Usable context
131K
Memory
512 GB
Fits in memory158 tok/sest · 131K ctx
Fits in memory134 tok/sest · 131K ctx
Fits in memory90 tok/sest · 131K ctx
What is quantisation? →
gpt-oss-120b
120B / 5.1B · full specs & benchmarks →
Apple M3 Ultra (80-core GPU)
512 GB · everything it runs →