Can I run this LLM?
Can a NVIDIA L40S (48GB) run North Mini Code 1.0 (MoE)?
North · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: North Mini Code 1.0 (MoE) at Q8_0 · 32.4 GB · 119–179 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.5 GB | 201–301 tok/s | Runs great |
| Q3_K_M | 14.2 GB | 180–270 tok/s | Runs great |
| Q4_K_M | 19.2 GB | 158–237 tok/s | Runs great |
| Q5_K_M | 23.0 GB | 145–217 tok/s | Runs great |
| Q6_K | 25.5 GB | 137–205 tok/s | Runs great |
| Q8_0 | 32.4 GB | 119–179 tok/s | Runs great |
| FP16 | 61.0 GB | 78–117 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA L40S (48GB) runsNorth Mini Code 1.0 (MoE) on other machinesWhat to buy to run it →
Ran North Mini Code 1.0 (MoE) on a NVIDIA L40S (48GB)? Add your real numbers →