Loading content...
Loading GPU benchmarks...
Apple M2 Ultra meets the minimum VRAM requirement for Q4 inference of unsloth/gemma-3-1b-it. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 1GB | 192GB | 125.77 tok/s | ✅ Fits comfortably |
| Q8 | 1GB | 192GB | 92.26 tok/s | ✅ Fits comfortably |
| FP16 | 2GB | 192GB | 46.48 tok/s | ✅ Fits comfortably |