AMD Ryzen AI Max 385~27 tok/s (Q4)

microsoft/VibeVoice-ASR speed on AMD Ryzen AI Max 385

Quantization-specific throughput and VRAM requirements for microsoft/VibeVoice-ASR running on AMD Ryzen AI Max 385.

Speed Snapshot

Topline estimate from compatibility data

Modelmicrosoft/VibeVoice-ASR

GPUAMD Ryzen AI Max 385

Q4 speed27 tok/s

Q4 VRAM required5GB

Data Source

Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Quantization Speed Table

Quantization	VRAM needed	VRAM available	Speed	Verdict
Q4	5GB	128GB	27 tok/s	✅ Fits
Q8	10GB	128GB	17 tok/s	✅ Fits
FP16	20GB	128GB	11 tok/s	✅ Fits