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

Compatibility check

Can I run Llama 3.2 3B Instruct on Apple M2 Ultra (76-core GPU)?

Yes — it runs.best quant:

Decode speed

289 tok/sest

Usable context

131K

Memory

192 GB

Fits in memory289 tok/sest · 131K ctx

Fits in memory246 tok/sest · 131K ctx

Fits in memory165 tok/sest · 131K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

Apple M2 Ultra (76-core GPU)

192 GB · everything it runs →