AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of microsoft/VibeVoice-1.5B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI300X can run microsoft/VibeVoice-1.5B with Q4 quantization. At approximately 793 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 189GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 3GB | 192GB | 793.37 tok/s | ✅ Fits comfortably |
| Q8 | 5GB | 192GB | 485.69 tok/s | ✅ Fits comfortably |
| FP16 | 11GB | 192GB | 300.90 tok/s | ✅ Fits comfortably |