GPU group

Cheap inference.

Mid-range GPUs that run quantized 7B–13B models at the lowest hourly rates.

GPU VRAM From
12GB $0.038/hr Compare →
16GB $0.048/hr Compare →
16GB $0.068/hr Compare →
12GB $0.076/hr Compare →
24GB $0.082/hr Compare →
12GB $0.091/hr Compare →
12GB $0.12/hr Compare →
16GB $0.12/hr Compare →
12GB $0.12/hr Compare →
16GB $0.13/hr Compare →
16GB $0.13/hr Compare →
12GB $0.16/hr Compare →
24GB $0.16/hr Compare →
12GB $0.17/hr Compare →
16GB $0.17/hr Compare →
20GB $0.18/hr Compare →
20GB $0.19/hr Compare →
12GB $0.19/hr Compare →
20GB $0.20/hr Compare →
24GB $0.21/hr Compare →
32GB $0.21/hr Compare →
24GB $0.26/hr Compare →
16GB $0.28/hr Compare →
32GB $0.29/hr Compare →
24GB $0.30/hr Compare →
48GB $0.32/hr Compare →
24GB $0.38/hr Compare →
32GB $0.41/hr Compare →
32GB $0.49/hr Compare →
16GB $0.50/hr Compare →
48GB $0.54/hr Compare →
48GB $0.63/hr Compare →
96GB $0.86/hr Compare →
96GB $0.91/hr Compare →
96GB $0.93/hr Compare →
96GB $0.99/hr Compare →
96GB $1.15/hr Compare →
96GB $1.69/hr Compare →
96GB $1.69/hr Compare →