can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Pro (48GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q5_K_M · 27.0 GB · 52–78 tok/s on a MacBook Pro M4 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB65–98 tok/sRuns great
Q3_K_M19.8 GB63–95 tok/sRuns great
Q4_K_M25.5 GB54–81 tok/sRuns great
Q5_K_M27.0 GB52–78 tok/sRuns great
Q6_K34.3 GB44–65 tok/sWon't fit
Q8_035.0 GB43–64 tok/sWon't fit
FP1665.9 GB26–39 tok/sWon't fit

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a MacBook Pro M4 Pro (48GB)? Add your real numbers →