NVIDIA H100 SXM5 80GB meets the minimum VRAM requirement for Q4 inference of mistralai/Mistral-Small-Instruct-2409. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H100 SXM5 80GB can run mistralai/Mistral-Small-Instruct-2409 with Q4 quantization. At approximately 295 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 69GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 11GB | 80GB | 294.85 tok/s | ✅ Fits comfortably |
| Q8 | 23GB | 80GB | 195.68 tok/s | ✅ Fits comfortably |
| FP16 | 46GB | 80GB | 93.62 tok/s | ✅ Fits comfortably |