// RUN ON CONSUMER GPU

Run Intern-S2-Preview on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 โ†’ ~79.5 yes 32k ~$1,999
NVIDIA GeForce RTX 4090 โ†’ ~44.7 tight 4k ~$1,599
NVIDIA GeForce RTX 3090 Ti โ†’ ~44.7 tight 4k ~$1,999
NVIDIA GeForce RTX 3090 โ†’ ~41.5 tight 4k ~$1,499
AMD Radeon RX 7900 XTX โ†’ ~37.7 tight 4k ~$999
Intel Arc Pro B70 โ†’ ~22.3 yes 32k โ€”
Intel Arc Pro B60 โ†’ ~16.8 tight 4k โ€”
NVIDIA DGX Spark โ†’ ~12.1 yes 359k ~$3,999
AMD Ryzen AI Max+ 395 โ†’ ~10.1 yes 359k ~$1,999

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

FAQ

What Consumer GPU hardware runs Intern-S2-Preview?โ–ถ

On GenAIList, 9 Consumer GPU options can run Intern-S2-Preview at Q4 โ€” the fastest is the NVIDIA GeForce RTX 5090 at ~79.5 tok/s.

How fast is Intern-S2-Preview on Consumer GPU hardware?โ–ถ

Estimated generation speed ranges from ~10.1 to ~79.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.