mavis-ai/Gemma4-31B-MLX

This repository contains the exact, unmodified base weights of the official Google Gemma 4 31B model.

⚠️ Important Notice While this repository is hosted primarily as a dedicated download source for our application ecosystem (R.E.V.I.S.), you are completely free to download and use these weights normally for your own MLX or local AI workflows. The weights are 100% identical to the official release. For all details regarding the model architecture, capabilities, and official documentation, you must refer directly to the Official google/gemma-4-31B page.

🚀 Optimized for R.E.V.I.S. (Local Cognitive OS)

We host this model to serve as the local reasoning engine for our project: R.E.V.I.S.

R.E.V.I.S. is a 100% local Cognitive OS for Multi-Agentic AI. It transforms your Mac devices into a distributed Agentic Swarm via zero-config Wi-Fi clustering, allowing you to run heavy AI workloads—like recursive web research, dynamic RAG generation, and multi-step logic—without killing single-machine performance.

If you are interested in pushing the absolute limits of local AI and open-weight models like this one, check out our project!

• 🌐 Official Website: https://mavis-ai.co.jp/revis/
• ▶️ Watch the 13-min Raw Demo (Multi-node Dynamic RAG): https://x.gd/LxaBF
• 🐦 Follow our updates on X: @mavis_ai_jp

License

This repository redistributes Google's Gemma 4 31B model, which is released by Google under the Apache License 2.0 (base model: google/gemma-4-31B).

These weights are redistributed unmodified under the same Apache License 2.0. A copy of the license is included in the LICENSE file in this repository, and can also be found at https://www.apache.org/licenses/LICENSE-2.0.

Notice: The weights in this repository are identical to the official release; no fine-tuning, quantization, or structural modifications have been applied.