LLMap
Models /GLM 4.5 Air /Can I run it?
Compatibility check

Can I run GLM 4.5 Air on Apple M2 Ultra (76-core GPU)?

Yes — it runs.best quant:
Decode speed
65 tok/sest
Usable context
131K
Memory
192 GB
Fits in memory65 tok/sest · 131K ctx
Fits in memory56 tok/sest · 131K ctx
Fits in memory37 tok/sest · 66K ctx
What is quantisation? →
GLM 4.5 Air
111B / 12B · full specs & benchmarks →
Apple M2 Ultra (76-core GPU)
192 GB · everything it runs →