Quantization-specific throughput and VRAM requirements for mistralai/Mistral-Large-Instruct-2411 running on NVIDIA A100 40GB PCIe.
Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.
For full verdict logic and alternate GPUs, see the canonical compatibility page.
Open full compatibility report| Quantization | VRAM needed | VRAM available | Speed | Verdict |
|---|---|---|---|---|
| Q4 | 60GB | 40GB | 46 tok/s | ❌ Not recommended |
| Q8 | 120GB | 40GB | 29 tok/s | ❌ Not recommended |
| FP16 | 240GB | 40GB | 16 tok/s | ❌ Not recommended |