AMD Instinct MI210~253 tok/s (Q4)

microsoft/Phi-3.5-mini-instruct speed on AMD Instinct MI210

Quantization-specific throughput and VRAM requirements for microsoft/Phi-3.5-mini-instruct running on AMD Instinct MI210.

Speed Snapshot

Topline estimate from compatibility data

Modelmicrosoft/Phi-3.5-mini-instruct

GPUAMD Instinct MI210

Q4 speed253 tok/s

Q4 VRAM required2GB

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	2GB	64GB	253 tok/s	✅ Fits
Q8	4GB	64GB	155 tok/s	✅ Fits
FP16	8GB	64GB	88 tok/s	✅ Fits