gemma3

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

A simple, performant, and scalable Jax LLM!

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Super lightweight Ollama + Qwen Code alternative to run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

Fine tune Gemma 3 on an object detection task

A JAX Research Toolkit for Visualizing, Manipulating, and Understanding Gemma Models with Multi-modal Support based on Penzai.

Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

Sparse-upcycle a dense Gemma-3-270m into a Mixture-of-Experts (gemma3moe) and serve it on llama.cpp (CPU). Upcycle, train, inspect routing, GGUF.

Platform for managing LLM fine-tuning (Google Summer of Code '25)

Detailed guide on Google's Gemma 3 AI

Gemma 3 [ Image-text-text ] [ video inference ] [ multi image chat ]