NVIDIA A5000~145 tok/s (Q4)

nari-labs/Dia2-2B speed on NVIDIA A5000

Quantization-specific throughput and VRAM requirements for nari-labs/Dia2-2B running on NVIDIA A5000.

Speed Snapshot

Topline estimate from compatibility data

Modelnari-labs/Dia2-2B

GPUNVIDIA A5000

Q4 speed145 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	24GB	145 tok/s	✅ Fits
Q8	3GB	24GB	111 tok/s	✅ Fits
FP16	5GB	24GB	57 tok/s	✅ Fits