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

Compatibility check

Can I run Llama 3.2 3B Instruct on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:

Decode speed

296 tok/sest

Usable context

131K

Memory

512 GB

Fits in memory296 tok/sest · 131K ctx

Fits in memory252 tok/sest · 131K ctx

Fits in memory169 tok/sest · 131K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

Apple M3 Ultra (80-core GPU)

512 GB · everything it runs →