Can I run this LLM?
Can a NVIDIA L40S (48GB) run Kimi Linear 48B-A3B (MoE)?
Kimi · MIT · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Kimi Linear 48B-A3B (MoE) at Q5_K_M · 35.0 GB · 162–243 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 16.0 GB | 230–344 tok/s | Runs great |
| Q3_K_M | 21.2 GB | 206–309 tok/s | Runs great |
| Q4_K_M | 29.8 GB | 176–264 tok/s | Runs great |
| Q5_K_M | 35.0 GB | 162–243 tok/s | Runs great |
| Q6_K | 40.5 GB | 149–224 tok/s | Tight / slow |
| Q8_0 | 52.2 GB | 128–192 tok/s | Won't fit |
| FP16 | 98.2 GB | 82–123 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA L40S (48GB) runsKimi Linear 48B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Kimi Linear 48B-A3B (MoE) on a NVIDIA L40S (48GB)? Add your real numbers →