AMD Instinct MI250X~165 tok/s (Q4)

01-ai/Yi-1.5-34B-Chat speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for 01-ai/Yi-1.5-34B-Chat running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

Model01-ai/Yi-1.5-34B-Chat

GPUAMD Instinct MI250X

Q4 speed165 tok/s

Q4 VRAM required18GB

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	18GB	128GB	165 tok/s	✅ Fits
Q8	35GB	128GB	119 tok/s	✅ Fits
FP16	70GB	128GB	67 tok/s	✅ Fits