Quantization-specific throughput and VRAM requirements for mistralai/Mistral-Small-Instruct-2409 running on NVIDIA A6000.
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 | 11GB | 48GB | 75 tok/s | ✅ Fits |
| Q8 | 23GB | 48GB | 52 tok/s | ✅ Fits |
| FP16 | 46GB | 48GB | 28 tok/s | ✅ Fits |