can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at FP16 · 17.6 GB · 15–23 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB53–79 tok/sRuns great
Q3_K_M4.4 GB45–68 tok/sRuns great
Q4_K_M5.4 GB40–59 tok/sRuns great
Q5_K_M6.3 GB36–53 tok/sRuns great
Q6_K7.2 GB32–48 tok/sRuns great
Q8_09.4 GB26–39 tok/sRuns great
FP1617.6 GB15–23 tok/sRuns great

Ran Granite 4.2 8B on a MacBook Pro M5 Max (36GB)? Add your real numbers →