// RUN ON CONSUMER GPU

Run Ovis1.6-Gemma2-9B on Consumer GPU hardware

28 options ranked by estimated speed at Q4 / 8k context.

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~272.9 yes 136k ~$1,999
NVIDIA GeForce RTX 4090 → ~153.5 yes 91k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~153.5 yes 91k ~$1,999
NVIDIA GeForce RTX 5080 → ~146.2 yes 46k ~$999
NVIDIA GeForce RTX 3090 → ~142.6 yes 91k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~138.9 yes 23k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~136.5 yes 46k ~$749
AMD Radeon RX 7900 XTX → ~129.4 yes 91k ~$999
NVIDIA GeForce RTX 3080 10GB → ~115.8 yes 12k ~$699
NVIDIA GeForce RTX 4080 → ~112.1 yes 46k ~$1,199
AMD Radeon RX 7900 XT → ~107.8 yes 68k ~$899
NVIDIA GeForce RTX 5070 → ~102.4 yes 23k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~102.4 yes 46k ~$799
AMD Radeon RX 9070 XT → ~86.8 yes 46k ~$599
AMD Radeon RX 7800 XT → ~84.1 yes 46k ~$499
NVIDIA GeForce RTX 4070 Super → ~76.8 yes 23k ~$599
NVIDIA GeForce RTX 4070 → ~76.8 yes 23k ~$599
Intel Arc Pro B70 → ~76.6 yes 136k —
Intel Arc A770 16GB → ~70.6 yes 46k ~$329
AMD Radeon RX 6800 XT → ~69 yes 46k ~$649
AMD Radeon RX 6900 XT → ~69 yes 46k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~68.2 yes 46k ~$429
Intel Arc Pro B60 → ~57.5 yes 91k —
Intel Arc B580 12GB → ~57.5 yes 23k ~$249
NVIDIA GeForce RTX 4060 Ti 16GB → ~43.9 yes 46k ~$499
NVIDIA DGX Spark → ~41.6 yes 659k ~$3,999
AMD Ryzen AI Max+ 395 → ~34.5 yes 659k ~$1,999
Intel Arc Pro B50 → ~28.2 yes 46k —

Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.

→ Ovis1.6-Gemma2-9B overview → All hardware

FAQ

What Consumer GPU hardware runs Ovis1.6-Gemma2-9B?▶

On GenAIList, 28 Consumer GPU options can run Ovis1.6-Gemma2-9B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~272.9 tok/s.

How fast is Ovis1.6-Gemma2-9B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~28.2 to ~272.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.