can-i-run-this-llm

Can I run this LLM?

Can a Mac mini M6 (32GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q2_K · 18.9 GB · 47–71 tok/s on a Mac mini M6 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB47–71 tok/sRuns great
Q3_K_M19.8 GB46–69 tok/sTight / slow
Q4_K_M25.5 GB38–57 tok/sWon't fit
Q5_K_M27.0 GB36–55 tok/sWon't fit
Q6_K34.3 GB30–45 tok/sWon't fit
Q8_035.0 GB29–44 tok/sWon't fit
FP1665.9 GB17–26 tok/sWon't fit

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a Mac mini M6 (32GB)? Add your real numbers →