AMD Instinct MI210~91 tok/s (Q4)

Qwen/Qwen2.5-32B-Instruct speed on AMD Instinct MI210

Quantization-specific throughput and VRAM requirements for Qwen/Qwen2.5-32B-Instruct running on AMD Instinct MI210.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen2.5-32B-Instruct

GPUAMD Instinct MI210

Q4 speed91 tok/s

Q4 VRAM required17GB

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	17GB	64GB	91 tok/s	✅ Fits
Q8	34GB	64GB	60 tok/s	✅ Fits
FP16	67GB	64GB	34 tok/s	❌ Not recommended