Gemma Python Packages

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

unsloth-zoo

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

pytorch-pretrained-bert

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

pytorch-transformers-pvt-nightly

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

jamma

JAMMA (Highly-Accelerated Multi-method Mixed-model Association) -- a fast and modern Python and C reimplementation of GEMMA for large-scale GWAS.

pytorch-transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

drydock-cli

Local-first TUI coding agent for Gemma 4 + llama.cpp. Built-in GraphRAG retrieval and cookbook of domain recipes. Install: pip install drydock-cli.

xinference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

decisio

A serving layer for decisions: typed questions in, a probability for every option out, one forward pass each. Three bases: Qwen3.6-35B-A3B, Gemma 4 12B, Gemma 4 31B.

oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

transformers4576

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

indigo-print

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

transformers-kt

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

rlinf-transformer-openpi

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

mogemma

🔥 Python / Mojo Interface for Google Gemma 4

screenmind

AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private.

developergpt

DeveloperGPT is a LLM-powered command line tool that enables natural language to terminal commands and in-terminal chat.

llmtuner

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

picollm

On-device LLM Inference Powered by X-Bit Quantization

picollmdemo

On-device LLM Inference Powered by X-Bit Quantization

redco

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference