Compatibility check
Can I run Llama 3 8B Lunaris on Apple M3 Pro (18-core GPU)?
Yes — it runs.best quant:
Decode speed
22 tok/sest
Usable context
8K
Memory
36 GB
Fits in memory22 tok/sest · 8K ctx
Fits in memory19 tok/sest · 8K ctx
Fits in memory12 tok/sest · 8K ctx