FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
Nexus Raven is a 13B instruction tuned model for function calling tasks.
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
https://huggingface.co/ibm-granite/granite-20b-functioncalling
Fine Tuned For Hermes-style function calling with VibeThinker 3b
Gemma 3 but with function calling.
Nio is a fine-tuned language model designed for function calling, AI agent integrations, and automated workflows.
The "Home" model is a fine tuning of the StableLM-Zephyr-3B model. It achieves a score of 97.11% score for JSON function calling accuracy.
A function calling LLM for use with the Home Assistant assist pipeline, based on llama3.1 8B
Mistral-7B fine tuned for function calling
A function calling model from the xLAM model family.
Function calling and structured JSON output
llava-NousResearch_Nous-Hermes-2-Vision-GGUF_Q4_0 with function calling
This is the llama.cpp GGUF Quantised version of Hermes 2 Pro Llama-3 8B from Nous Research with function calling capabilities.
Functionary Small v3.1 is a Llama 3.1 8b based tool calling LLM
Finetuned for function calling
Better in function calling.