Open models,
verified before deployment.

Different hardware runs different models. TechNode selects the right model for the job, quantizes it, and deploys only configurations that pass our accuracy and function-calling safety gate — matched to each hardware class. Every number below is our own measurement.

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 = ready to run on our serving infrastructure. Licenses are commercial-friendly (Apache/MIT) with exceptions noted — commercial use of EXAONE requires a license agreement with LG. Contact us →