NVIDIA L40S 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.
NVIDIA L40S can run deepseek-ai/deepseek-coder-1.3b-instruct with Q4 quantization. At approximately 214 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 46GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 48GB | 214.17 tok/s | ✅ Fits comfortably |
| Q8 | 3GB | 48GB | 141.27 tok/s | ✅ Fits comfortably |
| FP16 | 6GB | 48GB | 69.29 tok/s | ✅ Fits comfortably |