can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (256GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 256.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at FP16 · 65.9 GB · 76–114 tok/s on a Mac Studio M5 Ultra (256GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB126–189 tok/sRuns great
Q3_K_M19.8 GB124–187 tok/sRuns great
Q4_K_M25.5 GB115–173 tok/sRuns great
Q5_K_M27.0 GB113–170 tok/sRuns great
Q6_K34.3 GB104–156 tok/sRuns great
Q8_035.0 GB103–154 tok/sRuns great
FP1665.9 GB76–114 tok/sRuns great

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a Mac Studio M5 Ultra (256GB)? Add your real numbers →