In this video, I look at the latest release from the Gemma team, FunctionGemma, which is all about having a super-small model that you can use to do function calling at the edge.
In this video, we look at the latest release from Mistral, a new Mistral-3 large model and 3 Minstral models.
Blog: https://blog.google/technology/develo...
HF: https://huggingface.co/google/functio...
RAG on Device: / develop-an-on-device-rag-system-powered-by...
colab: https://colab.research.google.com/git...
For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: / samwitteveen
Twitter: https://x.com/Sam_Witteveen
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes
👨💻Github:
https://github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro
00:14 T5Gemma2
00:27 FunctionGemma Blog
02:47 What makes FunctionGemma Unique
03:24 On device RAG
04:07 Google AI Edge Gallery
04:46 FunctionGemma formatting and Best Practices
05:35 FunctionGemma HuggingFace
05:52 FunctionGemma Colab Demo
On this page of the site you can watch the video online FunctionGemma - Function Calling at the Edge with a duration of hours minute second in good quality, which was uploaded by the user Sam Witteveen 19 December 2025, share the link with friends and acquaintances, this video has already been watched 19,070 times on youtube and it was liked by 553 viewers. Enjoy your viewing!