Introducing Gemma 4 12B: a unified, encoder-free multimodal model

A Visual Guide to Gemma 4 12B

An in-depth explainer to Gemma 4 12B; a unified, encoder-free multimodal model!

Gemma 4 Technical Report

We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks.

Gemma 3n model overview  |  Google AI for Developers

Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets. This model includes innovations in parameter-efficient processing, including Per-Layer Embedding (PLE) parameter caching and a MatFormer model architecture that provides the flexibility to reduce compute and memory requirements. These models feature audio input handling, as well as text and visual data.

Matt Mireles on Twitter / X

Introducing...Gemma 4 Multimodal Fine-Tuner for  Apple Silicon- LoRA fine-tunning toolkit for Gemma LLM- runs locally on macOS via PyTorch and Metal- streams data from Google Cloud to your machine- fine-tune on audio, image and text- easy-to-use CLI wizardIf you want… pic.twitter.com/UduROxoxPU— Matt Mireles (@mattmireles) April 7, 2026

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

We’re releasing Gemma 4 quantization-aware training checkpoints, reducing memory requirements and improving on-device performance.

Gemma 4: Byte for byte, the most capable open models

Gemma 4: our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.

Unsloth AI on Twitter / X

Run Gemma 3n locally with our Dynamic GGUFs!✨@Google's Gemma 3n supports audio, vision, video & text and the 4B model fits on 8GB RAM for fast local inference.Fine-tuning is also supported in Unsloth.Gemma-3n-E4B GGUF: https://t.co/PliynxoKQc https://t.co/wMFWLjNaDR pic.twitter.com/lxsMNDmkW8— Unsloth AI (@UnslothAI) June 26, 2025

Simon Willison on Twitter / X

I'm really impressed by the new Gemma 3nI tried a 7.5GB model from Ollama and a 15GB model through mlx-vlm - they seem very capable, and this is the first model of that size I've tried that can handle both image AND audio input in addition to text! https://t.co/hiR3qGW387— Simon Willison (@simonw) June 26, 2025

gemma3n

Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.

Ensu continues

We're back to iterating on Ensu. The latest release brings Gemma 4, on-device voice transcription, and faster image queries.

Ollama's new engine for multimodal models· Ollama Blog

Ollama now supports new multimodal models with its new engine.

Google for Developers Blog - News about Web, Mobile, AI and Cloud

Learn how to build with Gemma 3n, a mobile-first architecture, MatFormer technology, Per-Layer Embeddings, and new audio and vision encoders.

Understanding Multimodal LLMs

An introduction to the main techniques and latest models

Apple Intelligence Foundation Language Models Tech Report 2025

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and…

qwen3.5:27b

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.