// RUN ON CONSUMER GPU

Run Flan UL2 on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~142.8 yes 65k ~$1,999
NVIDIA GeForce RTX 4090 → ~80.3 yes 37k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~80.3 yes 37k ~$1,999
NVIDIA GeForce RTX 5080 → ~76.5 yes 9k ~$999
NVIDIA GeForce RTX 3090 → ~74.6 yes 37k ~$1,499
NVIDIA GeForce RTX 5070 Ti → ~71.4 yes 9k ~$749
AMD Radeon RX 7900 XTX → ~67.7 yes 37k ~$999
NVIDIA GeForce RTX 4080 → ~58.6 yes 9k ~$1,199
AMD Radeon RX 7900 XT → ~56.4 yes 23k ~$899
NVIDIA GeForce RTX 4070 Ti Super → ~53.5 yes 9k ~$799
AMD Radeon RX 9070 XT → ~45.4 yes 9k ~$599
AMD Radeon RX 7800 XT → ~44 yes 9k ~$499
Intel Arc Pro B70 → ~40.1 yes 65k —
Intel Arc A770 16GB → ~36.9 yes 9k ~$329
AMD Radeon RX 6800 XT → ~36.1 yes 9k ~$649
AMD Radeon RX 6900 XT → ~36.1 yes 9k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~35.7 yes 9k ~$429
Intel Arc Pro B60 → ~30.1 yes 37k —
NVIDIA GeForce RTX 4060 Ti 16GB → ~22.9 yes 9k ~$499
NVIDIA DGX Spark → ~21.8 yes 392k ~$3,999
AMD Ryzen AI Max+ 395 → ~18.1 yes 392k ~$1,999
Intel Arc Pro B50 → ~14.8 yes 9k —

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

→ Flan UL2 overview → All hardware

FAQ

What Consumer GPU hardware runs Flan UL2?▶

On GenAIList, 22 Consumer GPU options can run Flan UL2 at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~142.8 tok/s.

How fast is Flan UL2 on Consumer GPU hardware?▶

Estimated generation speed ranges from ~14.8 to ~142.8 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.