Can I run this LLM?
Can a NVIDIA RTX 5070 Ti (16GB) run Qwen3 8B?
Qwen · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 8B at Q8_0 · 8.7 GB · 60–89 tok/s on a NVIDIA RTX 5070 Ti (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.3 GB | 116–175 tok/s | Runs great |
| Q3_K_M | 4.1 GB | 101–152 tok/s | Runs great |
| Q4_K_M | 5.0 GB | 89–133 tok/s | Runs great |
| Q5_K_M | 5.9 GB | 80–120 tok/s | Runs great |
| Q6_K | 6.7 GB | 72–109 tok/s | Runs great |
| Q8_0 | 8.7 GB | 60–89 tok/s | Runs great |
| FP16 | 16.4 GB | 35–53 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5070 Ti (16GB) runsQwen3 8B on other machinesWhat to buy to run it →
Ran Qwen3 8B on a NVIDIA RTX 5070 Ti (16GB)? Add your real numbers →