Open models,
sized to your GPU.

Different GPUs run different models, so we match each one to the GPU's power. A bigger GPU runs a bigger model, a smaller one runs a lighter one. Everything here we've run ourselves and checked for speed and function-calling — every number below is measured.

VRAM and tok/s measured on an RTX 4060 Ti 16GB (2026-06). accuracy ✓ = passes function-calling (calls a tool when needed, skips it when not). ● available now = the online GPU pool can run it right now. License: resale-friendly (Apache/MIT) only, exceptions noted. Pick one in the dashboard →