Apple M3 Max meets the minimum VRAM requirement for Q4 inference of 01-ai/Yi-1.5-34B-Chat. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M3 Max can run 01-ai/Yi-1.5-34B-Chat with Q4 quantization. At approximately 17 tokens/second, you can expect Basic speed - best for non-interactive tasks.
You have 110GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 18GB | 128GB | 17.20 tok/s | ✅ Fits comfortably |
| Q8 | 35GB | 128GB | 12.88 tok/s | ✅ Fits comfortably |
| FP16 | 70GB | 128GB | 7.09 tok/s | ✅ Fits comfortably |