Can I run this LLM?
Can a Mac Studio M3 Ultra (512GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?
Nemotron · openmdw-1.1 · estimated for a 512.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at FP16 · 65.9 GB · 60–90 tok/s on a Mac Studio M3 Ultra (512GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 18.9 GB | 111–167 tok/s | Runs great |
| Q3_K_M | 19.8 GB | 109–164 tok/s | Runs great |
| Q4_K_M | 25.5 GB | 99–149 tok/s | Runs great |
| Q5_K_M | 27.0 GB | 97–145 tok/s | Runs great |
| Q6_K | 34.3 GB | 87–130 tok/s | Runs great |
| Q8_0 | 35.0 GB | 86–129 tok/s | Runs great |
| FP16 | 65.9 GB | 60–90 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M3 Ultra (512GB) runsNemotron 3.5 Lightning 30B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a Mac Studio M3 Ultra (512GB)? Add your real numbers →