Compatibility check
Can I run Llama 3 8B Lunaris on Apple M4 Max (32-core GPU)?
Yes — it runs.best quant:
Decode speed
59 tok/sest
Usable context
8K
Memory
64 GB
Fits in memory59 tok/sest · 8K ctx
Fits in memory50 tok/sest · 8K ctx
Fits in memory34 tok/sest · 8K ctx