Models /Llama 3.2 3B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.2 3B Instruct on Apple M1 (8-core GPU, 8GB unified)?

Yes — it runs.best quant:

Decode speed

25 tok/sest

Usable context

66K

Memory

8 GB

Fits in memory25 tok/sest · 66K ctx

Fits in memory21 tok/sest · 66K ctx

Fits in memory14 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

Apple M1 (8-core GPU, 8GB unified)

8 GB · everything it runs →