Apple M4 Max meets the minimum VRAM requirement for Q4 inference of nari-labs/Dia2-2B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Max can run nari-labs/Dia2-2B with Q4 quantization. At approximately 84 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 126GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 128GB | 83.51 tok/s | ✅ Fits comfortably |
| Q8 | 3GB | 128GB | 56.11 tok/s | ✅ Fits comfortably |
| FP16 | 5GB | 128GB | 32.56 tok/s | ✅ Fits comfortably |