Models /GLM 4.5 Air /Can I run it?

Compatibility check

Can I run GLM 4.5 Air on Apple M4 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

45 tok/sest

Usable context

66K

Memory

128 GB

Fits in memory45 tok/sest · 66K ctx

Fits in memory38 tok/sest · 33K ctx

Spills to system RAM

What is quantisation? →

111B / 12B · full specs & benchmarks →

Apple M4 Max (40-core GPU)

128 GB · everything it runs →