Can I run this LLM?
Can a NVIDIA RTX 4090 (24GB) run Kimi Linear 48B-A3B (MoE)?
Kimi · MIT · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Kimi Linear 48B-A3B (MoE) at Q2_K · 16.0 GB · 242–364 tok/s on a NVIDIA RTX 4090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 16.0 GB | 242–364 tok/s | Runs great |
| Q3_K_M | 21.2 GB | 220–330 tok/s | Won't fit |
| Q4_K_M | 29.8 GB | 190–285 tok/s | Won't fit |
| Q5_K_M | 35.0 GB | 176–264 tok/s | Won't fit |
| Q6_K | 40.5 GB | 163–244 tok/s | Won't fit |
| Q8_0 | 52.2 GB | 141–211 tok/s | Won't fit |
| FP16 | 98.2 GB | 92–138 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 4090 (24GB) runsKimi Linear 48B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Kimi Linear 48B-A3B (MoE) on a NVIDIA RTX 4090 (24GB)? Add your real numbers →