Apple M2 Max meets the minimum VRAM requirement for Q4 inference of xgen-universe/Capybara. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M2 Max can run xgen-universe/Capybara with Q4 quantization. At approximately 53 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 92GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 96GB | 52.95 tok/s | ✅ Fits comfortably |
| Q8 | 8GB | 96GB | 38.89 tok/s | ✅ Fits comfortably |
| FP16 | 16GB | 96GB | 21.51 tok/s | ✅ Fits comfortably |