LLMap
Models /GLM 4.6V /Can I run it?
Compatibility check

Can I run GLM 4.6V on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:
Decode speed
8 tok/sest
Usable context
131K
Memory
512 GB
Fits in memory8 tok/sest · 131K ctx
Fits in memory6 tok/sest · 131K ctx
Fits in memory4 tok/sest · 131K ctx
What is quantisation? →
GLM 4.6V
108B · full specs & benchmarks →
Apple M3 Ultra (80-core GPU)
512 GB · everything it runs →