LLMap
Models /Magnum v4 72B /Can I run it?
Compatibility check

Can I run Magnum v4 72B on Apple M2 Max (38-core GPU)?

Yes — it runs.best quant:
Decode speed
6 tok/sest
Usable context
16K
Memory
96 GB
Fits in memory6 tok/sest · 16K ctx
Fits in memory5 tok/sest · 16K ctx
Spills to system RAM
What is quantisation? →
Magnum v4 72B
72.7B · full specs & benchmarks →
Apple M2 Max (38-core GPU)
96 GB · everything it runs →