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

Can I run GLM 4.5V on Apple M5 Max (40-core GPU)?

Yes — it runs.best quant:
Decode speed
6 tok/sest
Usable context
66K
Memory
128 GB
Fits in memory6 tok/sest · 66K ctx
Fits in memory5 tok/sest · 66K ctx
Spills to system RAM
What is quantisation? →
GLM 4.5V
108B · full specs & benchmarks →
Apple M5 Max (40-core GPU)
128 GB · everything it runs →