Compatibility check
Can I run Llama Guard 4 12B on Apple M5 (10-core GPU)?
Yes — it runs.best quant:
Decode speed
15 tok/sest
Usable context
131K
Memory
32 GB
Fits in memory15 tok/sest · 131K ctx
Fits in memory13 tok/sest · 131K ctx
Fits in memory8 tok/sest · 131K ctx