Can I run this LLM?
Can a NVIDIA H100 SXM (80GB) run Kimi Linear 48B-A3B (MoE)?
Kimi · MIT · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Kimi Linear 48B-A3B (MoE) at Q8_0 · 52.3 GB · 248–372 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 17.5 GB | 315–473 tok/s | Runs great |
| Q3_K_M | 22.7 GB | 303–455 tok/s | Runs great |
| Q4_K_M | 30.1 GB | 287–431 tok/s | Runs great |
| Q5_K_M | 35.1 GB | 277–416 tok/s | Runs great |
| Q6_K | 40.5 GB | 268–401 tok/s | Runs great |
| Q8_0 | 52.3 GB | 248–372 tok/s | Runs great |
| FP16 | 98.3 GB | 194–290 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsKimi Linear 48B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Kimi Linear 48B-A3B (MoE) on a NVIDIA H100 SXM (80GB)? Add your real numbers →