Compatibility check
Can I run GLM 4.5 Air on Apple M5 Max (40-core GPU)?
Yes — it runs.best quant:
Decode speed
50 tok/sest
Usable context
66K
Memory
128 GB
Fits in memory50 tok/sest · 66K ctx
Fits in memory43 tok/sest · 33K ctx
Spills to system RAM
