can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M1 Pro (32GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 14–21 tok/s on a MacBook Pro M1 Pro (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB34–51 tok/sRuns great
Q3_K_M3.5 GB28–42 tok/sRuns great
Q4_K_M4.9 GB22–33 tok/sRuns great
Q5_K_M5.7 GB19–29 tok/sRuns great
Q6_K6.6 GB17–25 tok/sRuns great
Q8_08.5 GB14–21 tok/sRuns great

Ran Llama 3.1 8B on a MacBook Pro M1 Pro (32GB)? Add your real numbers →