Vinod Chugani writes about how different open-weight model families—Gemma 4, Llama 3, and Mistral—implement tool calling for local deployments.The article explores the mechanisms of function calling, which allow models to interact with external APIs or data rather than relying solely on training data, and evaluates each model's unique architectural strengths and trade-offs regarding reliability, efficiency, and developer support.
- Gemma 4 offers native agentic support with a configurable thinking mode for intermediate reasoning.
- Llama 3 models include "pythonic" tool calling variants in specific smaller versions (1B/3B).
- Mistral Small leverages Mixture-of-Experts architecture to provide high efficiency on constrained hardware.
- Gemma 4 offers native agentic support with a configurable thinking mode for intermediate reasoning.
- Llama 3 models include "pythonic" tool calling variants in specific smaller versions (1B/3B).
- Mistral Small leverages Mixture-of-Experts architecture to provide high efficiency on constrained hardware.
Learn how to fine-tune large language models like Llama 3 for function calling, enabling interaction with external tools and APIs for tasks like web search and math operations.
Learn how to build an open LLM app using Hermes 2 Pro, a powerful LLM based on Meta's Llama 3 architecture. This tutorial explains how to deploy Hermes 2 Pro locally, create a function to track flight status using FlightAware API, and integrate it with the LLM.
