Model Library
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
The google/gemma-4-31B-it-Ultra is a highly capable, multimodal, dense open-weights model developed by Google DeepMind. Featuring 30.7 billion parameters and a massive 256,000-token context window, it excels in advanced reasoning, complex coding, and multimodal tasks (including text, high-resolution images, and video temporal reasoning). Released under the permissive Apache 2.0 license, this "Ultra" designation highlights its optimization for autonomous agent workflows, precise function calling, and structured data generation. When quantized (e.g., 4-bit), it can be comfortably run locally on consumer-grade hardware like a 24GB RTX 4090.
The google/gemma-4-31B-it-Ultra is a powerful, open-weights multimodal language and vision model developed by Google DeepMind. Designed to offer frontier-level capabilities in a relatively compact size, it excels in logical reasoning, coding, and autonomous workflows. It is released under the highly permissive Apache 2.0 license, making it ideal for both commercial deployment and research.
| Feature | Details |
|---|---|
| Architecture | Dense (all parameters active during inference) |
| Parameters | 30.7 Billion |
| Context Window | 256,000 tokens (256K) |
| Multimodal (Text, Image, Video in / Text, JSON out) |
| License | Apache 2.0 |
Despite its advanced capabilities, the model is highly accessible depending on the precision used:
