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

Can I run gpt-oss-120b on Apple M4 Max (40-core GPU)?

Yes — it runs.best quant:
Decode speed
105 tok/sest
Usable context
131K
Memory
128 GB
Fits in memory105 tok/sest · 131K ctx
Fits in memoryest90 tok/sest · 33K ctx
Spills to system RAMest
What is quantisation? →
gpt-oss-120b
120B / 5.1B · full specs & benchmarks →
Apple M4 Max (40-core GPU)
128 GB · everything it runs →