Google Releases Multimodal Gemma 4 31B Model
The new 31-billion-parameter model is an instruction-tuned, 'any-to-any' powerhouse released under a permissive Apache 2.0 license.
Google DeepMind has expanded its open model lineup with the release of Gemma 4 31B Instruct. This new model is a dense, 31-billion-parameter foundation model, marking a major update and the first entry in the Gemma 4 series.
The most significant feature of this release is its native multimodality. Described as an "any-to-any" model, Gemma 4 moves beyond text-only interactions to incorporate vision capabilities, allowing it to process and understand both text and images. This positions the model as a powerful tool for building more sophisticated, context-aware AI applications.
As an instruction-tuned model—specifically designated as an "assistant" variant—Gemma 4 31B has been fine-tuned to follow user prompts and engage in helpful dialogue. This makes it well-suited for direct integration into chatbots, creative tools, and other interactive products.
Continuing its commitment to open development, Google has released Gemma 4 under the commercially-friendly Apache 2.0 license. This allows developers and businesses to freely use, modify, and deploy the model. The official weights and model card are available on Hugging Face.
Sources
- Visit
google/gemma-4-31B-it-assistant
Hugging Face
More from Google DeepMind
All Google DeepMind releases →
EmbeddingGemma 2 Expands to Any Modality
Google DeepMind's compact embedding model now spans text, vision, audio, and video in a single vector space.
Google DeepMind's Gemma 4 Goes Multimodal and MoE
The new open-weights family adds a mixture-of-experts design, encoder-free multimodal inputs, and an optional thinking mode.
Google DeepMind Releases TabFM for Tabular Data
A new foundation model brings zero-shot, in-context learning to classification and regression on structured tables.
More in Any-to-Any
All Any-to-Any →
Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge
The 2-billion-parameter model combines vision, audio and speech-to-speech in a package small enough to run on device.
MiniMax Debuts M3.1 Flash, a Multimodal MoE Model
The new release pairs a mixture-of-experts design with agentic, coding, and video-understanding abilities in a single open model.
IBM's Granite Switch 4.1 Unifies Chat, Logic, Speech
A single endpoint now routes text conversation, decision-making, and speech synthesis across IBM's Apache-licensed Granite line.
0 comments
No comments yet. Be the first to weigh in.