can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (64GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 44–66 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB86–129 tok/sRuns great
Q3_K_M3.5 GB76–113 tok/sRuns great
Q4_K_M4.9 GB63–95 tok/sRuns great
Q5_K_M5.7 GB57–86 tok/sRuns great
Q6_K6.6 GB52–79 tok/sRuns great
Q8_08.5 GB44–66 tok/sRuns great

Ran Llama 3.1 8B on a Mac Studio M1 Ultra (64GB)? Add your real numbers →