AMD Instinct MI250X~476 tok/s (Q4)

meta-llama/Llama-3.2-3B-Instruct speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for meta-llama/Llama-3.2-3B-Instruct running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

Modelmeta-llama/Llama-3.2-3B-Instruct

GPUAMD Instinct MI250X

Q4 speed476 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	128GB	476 tok/s	✅ Fits
Q8	3GB	128GB	348 tok/s	✅ Fits
FP16	7GB	128GB	174 tok/s	✅ Fits