// RUN ON CONSUMER GPU

Run VILA1.5-13B on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~206.3 yes 124k ~$1,999
NVIDIA GeForce RTX 4090 → ~116.1 yes 79k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~116.1 yes 79k ~$1,999
NVIDIA GeForce RTX 5080 → ~110.5 yes 35k ~$999
NVIDIA GeForce RTX 3090 → ~107.8 yes 79k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~105 yes 12k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~103.2 yes 35k ~$749
AMD Radeon RX 7900 XTX → ~97.8 yes 79k ~$999
NVIDIA GeForce RTX 4080 → ~84.7 yes 35k ~$1,199
AMD Radeon RX 7900 XT → ~81.5 yes 57k ~$899
NVIDIA GeForce RTX 5070 → ~77.4 yes 12k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~77.4 yes 35k ~$799
AMD Radeon RX 9070 XT → ~65.6 yes 35k ~$599
AMD Radeon RX 7800 XT → ~63.6 yes 35k ~$499
NVIDIA GeForce RTX 4070 Super → ~58 yes 12k ~$599
NVIDIA GeForce RTX 4070 → ~58 yes 12k ~$599
Intel Arc Pro B70 → ~57.9 yes 124k —
Intel Arc A770 16GB → ~53.4 yes 35k ~$329
AMD Radeon RX 6800 XT → ~52.2 yes 35k ~$649
AMD Radeon RX 6900 XT → ~52.2 yes 35k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~51.6 yes 35k ~$429
Intel Arc Pro B60 → ~43.4 yes 79k —
Intel Arc B580 12GB → ~43.4 yes 12k ~$249
NVIDIA GeForce RTX 4060 Ti 16GB → ~33.2 yes 35k ~$499
NVIDIA DGX Spark → ~31.4 yes 648k ~$3,999
AMD Ryzen AI Max+ 395 → ~26.1 yes 648k ~$1,999
Intel Arc Pro B50 → ~21.3 yes 35k —

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

→ VILA1.5-13B overview → All hardware

FAQ

What Consumer GPU hardware runs VILA1.5-13B?▶

On GenAIList, 27 Consumer GPU options can run VILA1.5-13B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~206.3 tok/s.

How fast is VILA1.5-13B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~21.3 to ~206.3 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.