// RUN ON CONSUMER GPU

Run GPT-2 (774M) on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~3,596.9 yes 420k ~$1,999
NVIDIA GeForce RTX 4090 → ~2,023.3 yes 307k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~2,023.3 yes 307k ~$1,999
NVIDIA GeForce RTX 5080 → ~1,926.9 yes 195k ~$999
NVIDIA GeForce RTX 3090 → ~1,878.7 yes 307k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~1,830.6 yes 139k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~1,798.4 yes 195k ~$749
AMD Radeon RX 7900 XTX → ~1,705.4 yes 307k ~$999
NVIDIA GeForce RTX 3080 10GB → ~1,525.5 yes 111k ~$699
NVIDIA GeForce RTX 4080 → ~1,477.3 yes 195k ~$1,199
AMD Radeon RX 7900 XT → ~1,421.2 yes 251k ~$899
NVIDIA GeForce RTX 5070 → ~1,348.8 yes 139k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~1,348.8 yes 195k ~$799
NVIDIA GeForce RTX 3070 Ti → ~1,220.4 yes 83k ~$599
AMD Radeon RX 9070 XT → ~1,144.1 yes 195k ~$599
AMD Radeon RX 7800 XT → ~1,108.5 yes 195k ~$499
NVIDIA GeForce RTX 4070 Super → ~1,011.6 yes 139k ~$599
NVIDIA GeForce RTX 4070 → ~1,011.6 yes 139k ~$599
Intel Arc Pro B70 → ~1,010 yes 420k —
Intel Arc A770 16GB → ~930.2 yes 195k ~$329
AMD Radeon RX 6800 XT → ~909.6 yes 195k ~$649
AMD Radeon RX 6900 XT → ~909.6 yes 195k ~$999
NVIDIA GeForce RTX 3070 → ~899.2 yes 83k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~899.2 yes 195k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~899.2 yes 83k ~$379
Intel Arc Pro B60 → ~757.5 yes 307k —
Intel Arc B580 12GB → ~757.5 yes 139k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~578.1 yes 83k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~578.1 yes 195k ~$499
NVIDIA DGX Spark → ~548 yes 1728k ~$3,999
AMD Ryzen AI Max+ 395 → ~454.8 yes 1728k ~$1,999
Intel Arc Pro B50 → ~372.1 yes 195k —
NVIDIA GeForce RTX 2050 Mobile → ~224.8 yes 27k —

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

→ GPT-2 (774M) overview → All hardware

FAQ

What Consumer GPU hardware runs GPT-2 (774M)?▶

On GenAIList, 33 Consumer GPU options can run GPT-2 (774M) at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~3,596.9 tok/s.

How fast is GPT-2 (774M) on Consumer GPU hardware?▶

Estimated generation speed ranges from ~224.8 to ~3,596.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.