Compatibility check
Can I run Llama Guard 4 12B on Apple M3 (10-core GPU)?
Yes — it runs.best quant:
Decode speed
10 tok/sest
Usable context
131K
Memory
24 GB
Fits in memory10 tok/sest · 131K ctx
Fits in memory8 tok/sest · 66K ctx
Fits in memory6 tok/sest · 33K ctx