can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Pro (18GB) run Llama 3.2 3B?

Llama · Llama 3.2 Community · estimated for a 18.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.2 3B at FP16 · 6.4 GB · 14–20 tok/s on a MacBook Pro M3 Pro (18GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.9 GB34–50 tok/sRuns great
Q5_K_M2.3 GB30–45 tok/sRuns great
Q6_K2.6 GB27–41 tok/sRuns great
Q8_03.4 GB23–34 tok/sRuns great
FP166.4 GB14–20 tok/sRuns great

Ran Llama 3.2 3B on a MacBook Pro M3 Pro (18GB)? Add your real numbers →