Models /Llama Guard 4 12B /Can I run it?

Compatibility check

Can I run Llama Guard 4 12B on Apple M1 Max (32-core GPU)?

Yes — it runs.best quant:

Decode speed

39 tok/sest

Usable context

262K

Memory

64 GB

Fits in memory39 tok/sest · 262K ctx

Fits in memory33 tok/sest · 262K ctx

Fits in memory22 tok/sest · 262K ctx

What is quantisation? →

Llama Guard 4 12B

12B · full specs & benchmarks →

Apple M1 Max (32-core GPU)

64 GB · everything it runs →