FW-Gemma-4-31B-IT

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Non-Microsoft Product. The following terms apply to a Customer's use of Fireworks on Foundry: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, Customer Data will be sent outside of Microsoft systems, Customer Data will not be processed pursuant to any Foundry data residency documentation, and different compliance and data handling rules will apply. See Trust Center - Fireworks AI for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization's compliance requirements.

About this model

Gemma 4 31B IT is the 31B dense variant in Google DeepMind's Gemma 4 family, with 30.7B parameters, 60 layers, a 1,024-token sliding window, and a ~550M vision encoder. It supports text and image inputs and generates text output, with image handling that includes variable aspect ratio and resolution support across Gemma 4 models. Gemma 4 introduces configurable thinking modes for reasoning, and this variant supports up to a 256K-token context window with multilingual support in over 140 languages.

Key model capabilities

• Text and image input with text output
• 256K-token context window
• Configurable thinking modes for reasoning
• Multilingual support in over 140 languages
• Image support with variable aspect ratio and resolution