Can I run this LLM?
Can a NVIDIA L40S (48GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at Q8_0 · 29.1 GB · 20–31 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.8 GB | 50–75 tok/s | Runs great |
| Q3_K_M | 13.4 GB | 41–62 tok/s | Runs great |
| Q4_K_M | 17.4 GB | 33–49 tok/s | Runs great |
| Q5_K_M | 20.9 GB | 28–42 tok/s | Runs great |
| Q6_K | 23.9 GB | 25–37 tok/s | Runs great |
| Q8_0 | 29.1 GB | 20–31 tok/s | Runs great |
| FP16 | 54.7 GB | 11–17 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA L40S (48GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a NVIDIA L40S (48GB)? Add your real numbers →