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 121 days ago. Current rank #337. Down 3 spots in the rankings.
A 150M ModernBERT-based token classification model that extracts verbatim evidence spans for RAG and related pipelines, reducing the need for an LLM call to highlight answers.
JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.
A vision-language foundation model for autonomous driving that combines 3D perception, driving VQA, and motion planning in one framework. The repo shows performance tables, model structure, and links to the paper, blog, and model downloads.
