Compatibility check
Can I run Mistral Small 3.1 24B on Apple M3 Max (40-core GPU)?
Yes — it runs.best quant:
Decode speed
19 tok/sest
Usable context
66K
Memory
128 GB
Fits in memory19 tok/sest · 66K ctx
Fits in memory16 tok/sest · 66K ctx
Fits in memory11 tok/sest · 66K ctx