Models /Olmo 3 32B Think /Can I run it?

Compatibility check

Can I run Olmo 3 32B Think on Apple M4 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

20 tok/sest

Usable context

66K

Memory

128 GB

Fits in memory20 tok/sest · 66K ctx

Fits in memory17 tok/sest · 66K ctx

Fits in memory11 tok/sest · 66K ctx

What is quantisation? →

Olmo 3 32B Think

32.2B · full specs & benchmarks →

Apple M4 Max (40-core GPU)

128 GB · everything it runs →