AMD Instinct MI300X 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.
AMD Instinct MI300X can run 01-ai/Yi-1.5-34B-Chat with Q4 quantization. At approximately 250 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 174GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 18GB | 192GB | 249.89 tok/s | ✅ Fits comfortably |
| Q8 | 35GB | 192GB | 185.13 tok/s | ✅ Fits comfortably |
| FP16 | 70GB | 192GB | 101.02 tok/s | ✅ Fits comfortably |