// RUN ON CONSUMER GPU

Run Gemma 1.1 7B Instruct 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 → ~326 yes 177k ~$1,999
NVIDIA GeForce RTX 4090 → ~183.4 yes 121k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~183.4 yes 121k ~$1,999
NVIDIA GeForce RTX 5080 → ~174.6 yes 64k ~$999
NVIDIA GeForce RTX 3090 → ~170.3 yes 121k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~165.9 yes 36k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~163 yes 64k ~$749
AMD Radeon RX 7900 XTX → ~154.6 yes 121k ~$999
NVIDIA GeForce RTX 3080 10GB → ~138.3 yes 22k ~$699
NVIDIA GeForce RTX 4080 → ~133.9 yes 64k ~$1,199
AMD Radeon RX 7900 XT → ~128.8 yes 92k ~$899
NVIDIA GeForce RTX 5070 → ~122.2 yes 36k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~122.2 yes 64k ~$799
NVIDIA GeForce RTX 3070 Ti → ~110.6 yes 8k ~$599
AMD Radeon RX 9070 XT → ~103.7 yes 64k ~$599
AMD Radeon RX 7800 XT → ~100.5 yes 64k ~$499
NVIDIA GeForce RTX 4070 Super → ~91.7 yes 36k ~$599
NVIDIA GeForce RTX 4070 → ~91.7 yes 36k ~$599
Intel Arc Pro B70 → ~91.5 yes 177k —
Intel Arc A770 16GB → ~84.3 yes 64k ~$329
AMD Radeon RX 6800 XT → ~82.4 yes 64k ~$649
AMD Radeon RX 6900 XT → ~82.4 yes 64k ~$999
NVIDIA GeForce RTX 3070 → ~81.5 yes 8k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~81.5 yes 64k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~81.5 yes 8k ~$379
Intel Arc Pro B60 → ~68.7 yes 121k —
Intel Arc B580 12GB → ~68.7 yes 36k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~52.4 yes 8k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~52.4 yes 64k ~$499
NVIDIA DGX Spark → ~49.7 yes 831k ~$3,999
AMD Ryzen AI Max+ 395 → ~41.2 yes 831k ~$1,999
Intel Arc Pro B50 → ~33.7 yes 64k —

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

→ Gemma 1.1 7B Instruct overview → All hardware

FAQ

What Consumer GPU hardware runs Gemma 1.1 7B Instruct?▶

On GenAIList, 32 Consumer GPU options can run Gemma 1.1 7B Instruct at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~326 tok/s.

How fast is Gemma 1.1 7B Instruct on Consumer GPU hardware?▶

Estimated generation speed ranges from ~33.7 to ~326 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.