// RUN ON CONSUMER GPU

Run Granite 3.2 2B 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 → ~1,100.4 yes 405k ~$1,999
NVIDIA GeForce RTX 4090 → ~619 yes 292k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~619 yes 292k ~$1,999
NVIDIA GeForce RTX 5080 → ~589.5 yes 180k ~$999
NVIDIA GeForce RTX 3090 → ~574.8 yes 292k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~560 yes 124k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~550.2 yes 180k ~$749
AMD Radeon RX 7900 XTX → ~521.7 yes 292k ~$999
NVIDIA GeForce RTX 3080 10GB → ~466.7 yes 96k ~$699
NVIDIA GeForce RTX 4080 → ~451.9 yes 180k ~$1,199
AMD Radeon RX 7900 XT → ~434.8 yes 236k ~$899
NVIDIA GeForce RTX 5070 → ~412.6 yes 124k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~412.6 yes 180k ~$799
NVIDIA GeForce RTX 3070 Ti → ~373.3 yes 68k ~$599
AMD Radeon RX 9070 XT → ~350 yes 180k ~$599
AMD Radeon RX 7800 XT → ~339.1 yes 180k ~$499
NVIDIA GeForce RTX 4070 Super → ~309.5 yes 124k ~$599
NVIDIA GeForce RTX 4070 → ~309.5 yes 124k ~$599
Intel Arc Pro B70 → ~309 yes 405k —
Intel Arc A770 16GB → ~284.6 yes 180k ~$329
AMD Radeon RX 6800 XT → ~278.3 yes 180k ~$649
AMD Radeon RX 6900 XT → ~278.3 yes 180k ~$999
NVIDIA GeForce RTX 3070 → ~275.1 yes 68k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~275.1 yes 180k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~275.1 yes 68k ~$379
Intel Arc Pro B60 → ~231.7 yes 292k —
Intel Arc B580 12GB → ~231.7 yes 124k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~176.8 yes 68k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~176.8 yes 180k ~$499
NVIDIA DGX Spark → ~167.6 yes 1713k ~$3,999
AMD Ryzen AI Max+ 395 → ~139.1 yes 1713k ~$1,999
Intel Arc Pro B50 → ~113.8 yes 180k —
NVIDIA GeForce RTX 2050 Mobile → ~68.8 yes 12k —

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

→ Granite 3.2 2B overview → All hardware

FAQ

What Consumer GPU hardware runs Granite 3.2 2B?▶

On GenAIList, 33 Consumer GPU options can run Granite 3.2 2B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~1,100.4 tok/s.

How fast is Granite 3.2 2B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~68.8 to ~1,100.4 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.