RTX 5090 meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-Coder-1.5B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
RTX 5090 can run Qwen/Qwen2.5-Coder-1.5B with Q4 quantization. At approximately 280 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 29GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 3GB | 32GB | 280.21 tok/s | ✅ Fits comfortably |
| Q8 | 5GB | 32GB | 223.22 tok/s | ✅ Fits comfortably |
| FP16 | 11GB | 32GB | 108.71 tok/s | ✅ Fits comfortably |