can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (64GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at FP16 · 17.6 GB · 25–38 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB75–112 tok/sRuns great
Q3_K_M4.4 GB66–99 tok/sRuns great
Q4_K_M5.4 GB59–88 tok/sRuns great
Q5_K_M6.3 GB54–80 tok/sRuns great
Q6_K7.2 GB49–73 tok/sRuns great
Q8_09.4 GB41–61 tok/sRuns great
FP1617.6 GB25–38 tok/sRuns great

Ran Granite 4.2 8B on a Mac Studio M1 Ultra (64GB)? Add your real numbers →