AMD Instinct MI210 meets the minimum VRAM requirement for Q4 inference of mistralai/Mistral-Large-Instruct-2411. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI210 can run mistralai/Mistral-Large-Instruct-2411 with Q4 quantization. At approximately 51 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 4GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 60GB | 64GB | 50.71 tok/s | ✅ Fits comfortably |
| Q8 | 120GB | 64GB | 33.30 tok/s | ❌ Not recommended |
| FP16 | 240GB | 64GB | 17.18 tok/s | ❌ Not recommended |