RTX 5090 meets the minimum VRAM requirement for Q4 inference of deepseek-ai/deepseek-coder-1.3b-instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
RTX 5090 can run deepseek-ai/deepseek-coder-1.3b-instruct with Q4 quantization. At approximately 371 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 30GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 32GB | 371.04 tok/s | ✅ Fits comfortably |
| Q8 | 3GB | 32GB | 264.59 tok/s | ✅ Fits comfortably |
| FP16 | 6GB | 32GB | 126.71 tok/s | ✅ Fits comfortably |