Loading content...
Loading GPU benchmarks...
Apple M3 Max meets the minimum VRAM requirement for Q4 inference of numind/NuExtract-1.5. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 128GB | 55.76 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 128GB | 37.05 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 128GB | 22.05 tok/s | ✅ Fits comfortably |