Models /Llama 3.2 1B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.2 1B Instruct on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:

Decode speed

788 tok/sest

Usable context

33K

Memory

512 GB

Fits in memory788 tok/sest · 33K ctx

Fits in memory672 tok/sest · 33K ctx

Fits in memory450 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

Apple M3 Ultra (80-core GPU)

512 GB · everything it runs →