# Function Call Optimization

Phi-4-mini-instruct is a lightweight open-source model focused on high-quality, reasoning-rich data, supporting a context length of 128K tokens.

DeepSeek-V3-0324 is a BF16 version large language model released by DeepSeek AI, suitable for quantization and inference on GPUs that do not support FP8.

DeepHermes 3 Preview Abliterated is the latest version of Nous Research's flagship Hermes series large language model, integrating reasoning and conventional LLM response modes.

Mistral Small 3 (version 2501) is a 24B-parameter instruction-tuned large language model that sets a new benchmark in the sub-70B parameter category, featuring exceptional knowledge density and multilingual support capabilities.

xLAM-7b-fc-r is a 7B-parameter large language model optimized for function calls, developed by Salesforce, capable of providing fast, accurate, and structured responses based on input queries and available APIs.

xLAM-1b-fc-r is a small-scale Large Action Model (LAM) optimized for function calls, developed by Salesforce, with 1.35B parameters, suitable for deployment on personal devices.

Granite-20B-FunctionCalling is fine-tuned from IBM's granite-20b-code-instruct model, specifically designed for function calling tasks and supports seven core functionalities.

The 70-billion-parameter version of the Llama 3 Groq tool-use model, specifically designed for advanced tool usage and function calling tasks.

FireFunction V2 is a state-of-the-art function calling model developed by Fireworks AI with a commercially viable license. It is trained on Llama 3 and supports parallel function calls with strong instruction-following capabilities.

FireFunction V2 is a state-of-the-art function calling model with a commercially viable license, trained on Llama 3, supporting parallel function calls and strong instruction following.

A model fine-tuned based on Vistral-7B-chat, supporting function calling.

A function-calling model fine-tuned based on Mistral-7B, supporting natural language understanding and function calling capabilities.

Llama 2 7B chat model, fine-tuned for function calling capabilities, supports OpenAI-style function metadata format, suitable for commercial use.