AMD Instinct MI300X~950 tok/s (Q4)

allenai/OLMo-2-0425-1B speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for allenai/OLMo-2-0425-1B running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modelallenai/OLMo-2-0425-1B

GPUAMD Instinct MI300X

Q4 speed950 tok/s

Q4 VRAM required1GB

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	1GB	192GB	950 tok/s	✅ Fits
Q8	1GB	192GB	666 tok/s	✅ Fits
FP16	2GB	192GB	377 tok/s	✅ Fits