AI Model / Function Calling
An open-source 26M parameter function-calling model designed to run on very small devices, with a local quickstart, Python usage, and a playground for testing and finetuning.
The page clearly presents an AI product with a specific purpose: a tiny function-calling model for on-device use. The README gives enough evidence for a useful listing, including what it does, how to run it locally, Python inference examples, and CLI commands for playground, finetuning, training, evaluation, and data generation.
The snapshot does not show benchmark details, supported hardware limits, licensing of the weights beyond the repo license, or how well it performs outside single-shot tool calling. It also does not fully explain the dataset, evaluation setup, or integration requirements for real apps.
Last evaluated 20 days ago. Current rank #53. Down 3 spots in the rankings.
JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.
