can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (64GB) run Gemma 2 2B?

Gemma · Gemma · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 2 2B at Q8_0 · 2.8 GB · 85–127 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.6 GB105–157 tok/sRuns great
Q5_K_M1.9 GB99–149 tok/sRuns great
Q6_K2.2 GB94–141 tok/sRuns great
Q8_02.8 GB85–127 tok/sRuns great

Ran Gemma 2 2B on a Mac Studio M1 Ultra (64GB)? Add your real numbers →