AMD Ryzen AI Max+ 395 meets the minimum VRAM requirement for Q4 inference of microsoft/VibeVoice-ASR. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Ryzen AI Max+ 395 can run microsoft/VibeVoice-ASR with Q4 quantization. At approximately 28 tokens/second, you can expect Moderate speed - useful for batch processing.
You have 123GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 5GB | 128GB | 28.42 tok/s | ✅ Fits comfortably |
| Q8 | 10GB | 128GB | 19.53 tok/s | ✅ Fits comfortably |
| FP16 | 20GB | 128GB | 10.31 tok/s | ✅ Fits comfortably |