RX 9070 XT~117 tok/s (Q4)

nari-labs/Dia2-2B speed on RX 9070 XT

Quantization-specific throughput and VRAM requirements for nari-labs/Dia2-2B running on RX 9070 XT.

Speed Snapshot

Topline estimate from compatibility data

Modelnari-labs/Dia2-2B

GPURX 9070 XT

Q4 speed117 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	16GB	117 tok/s	✅ Fits
Q8	3GB	16GB	76 tok/s	✅ Fits
FP16	5GB	16GB	47 tok/s	✅ Fits