Can I run this LLM?
Can a NVIDIA L40S (48GB) run Qwen3 14B?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 14B at FP16 · 29.5 GB · 20–30 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 5.8 GB | 78–117 tok/s | Runs great |
| Q3_K_M | 7.3 GB | 66–98 tok/s | Runs great |
| Q4_K_M | 9.0 GB | 56–84 tok/s | Runs great |
| Q5_K_M | 10.5 GB | 49–74 tok/s | Runs great |
| Q6_K | 12.1 GB | 44–66 tok/s | Runs great |
| Q8_0 | 15.7 GB | 35–53 tok/s | Runs great |
| FP16 | 29.5 GB | 20–30 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA L40S (48GB) runsQwen3 14B on other machinesWhat to buy to run it →
Ran Qwen3 14B on a NVIDIA L40S (48GB)? Add your real numbers →