NVIDIA L40S meets the minimum VRAM requirement for Q4 inference of deepseek-ai/DeepSeek-R1-Distill-Llama-8B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA L40S can run deepseek-ai/DeepSeek-R1-Distill-Llama-8B with Q4 quantization. At approximately 174 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 44GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 48GB | 174.25 tok/s | ✅ Fits comfortably |
| Q8 | 9GB | 48GB | 120.50 tok/s | ✅ Fits comfortably |
| FP16 | 17GB | 48GB | 64.20 tok/s | ✅ Fits comfortably |