// RUN ON CONSUMER GPU

Run EXAONE 3.0 on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 โ†’ ~356 yes 180k ~$1,999
NVIDIA GeForce RTX 4090 โ†’ ~200.3 yes 124k ~$1,599
NVIDIA GeForce RTX 3090 Ti โ†’ ~200.3 yes 124k ~$1,999
NVIDIA GeForce RTX 5080 โ†’ ~190.7 yes 67k ~$999
NVIDIA GeForce RTX 3090 โ†’ ~186 yes 124k ~$1,499
NVIDIA GeForce RTX 3080 Ti โ†’ ~181.2 yes 39k ~$1,199
NVIDIA GeForce RTX 5070 Ti โ†’ ~178 yes 67k ~$749
AMD Radeon RX 7900 XTX โ†’ ~168.8 yes 124k ~$999
NVIDIA GeForce RTX 3080 10GB โ†’ ~151 yes 25k ~$699
NVIDIA GeForce RTX 4080 โ†’ ~146.2 yes 67k ~$1,199
AMD Radeon RX 7900 XT โ†’ ~140.7 yes 96k ~$899
NVIDIA GeForce RTX 5070 โ†’ ~133.5 yes 39k ~$549
NVIDIA GeForce RTX 4070 Ti Super โ†’ ~133.5 yes 67k ~$799
NVIDIA GeForce RTX 3070 Ti โ†’ ~120.8 yes 11k ~$599
AMD Radeon RX 9070 XT โ†’ ~113.2 yes 67k ~$599
AMD Radeon RX 7800 XT โ†’ ~109.7 yes 67k ~$499
NVIDIA GeForce RTX 4070 Super โ†’ ~100.1 yes 39k ~$599
NVIDIA GeForce RTX 4070 โ†’ ~100.1 yes 39k ~$599
Intel Arc Pro B70 โ†’ ~100 yes 180k โ€”
Intel Arc A770 16GB โ†’ ~92.1 yes 67k ~$329
AMD Radeon RX 6800 XT โ†’ ~90 yes 67k ~$649
AMD Radeon RX 6900 XT โ†’ ~90 yes 67k ~$999
NVIDIA GeForce RTX 3070 โ†’ ~89 yes 11k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB โ†’ ~89 yes 67k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB โ†’ ~89 yes 11k ~$379
Intel Arc Pro B60 โ†’ ~75 yes 124k โ€”
Intel Arc B580 12GB โ†’ ~75 yes 39k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB โ†’ ~57.2 yes 11k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB โ†’ ~57.2 yes 67k ~$499
NVIDIA DGX Spark โ†’ ~54.2 yes 834k ~$3,999
AMD Ryzen AI Max+ 395 โ†’ ~45 yes 834k ~$1,999
Intel Arc Pro B50 โ†’ ~36.8 yes 67k โ€”

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

FAQ

What Consumer GPU hardware runs EXAONE 3.0?โ–ถ

On GenAIList, 32 Consumer GPU options can run EXAONE 3.0 at Q4 โ€” the fastest is the NVIDIA GeForce RTX 5090 at ~356 tok/s.

How fast is EXAONE 3.0 on Consumer GPU hardware?โ–ถ

Estimated generation speed ranges from ~36.8 to ~356 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.