AMD Instinct MI300X~546 tok/s (Q4)

google/gemma-2-9b-it speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for google/gemma-2-9b-it running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modelgoogle/gemma-2-9b-it

GPUAMD Instinct MI300X

Q4 speed546 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	192GB	546 tok/s	✅ Fits
Q8	10GB	192GB	394 tok/s	✅ Fits
FP16	20GB	192GB	224 tok/s	✅ Fits