Text · Released Apr 2026
Google Gemma 4 31B
Google's flagship 31B dense model with 256K context and top-tier text and image understanding.
From Google, Gemma 4 31B is an open-weight text model. It is multimodal: alongside a text prompt it accepts images, then replies with generated text. It runs entirely on your own hardware through Ollama: no API key and no per-use fees.
Supported OS
macOSWindowsLinux
Minimum machine configuration
32 GB+ RAM · 256K ctx · text+image · GPU strongly recommended
Download size · ~20 GB
Specs
- Released
- 5 months ago (Apr 2026)
- Pricing
- Free, runs on your hardware
- Inputs
- Text, Images
About the creator
Google and Google DeepMind build the Gemini family of multimodal models, the Imagen and Nano Banana image models, the Lyria music models, and the Veo video models.
deepmind.google ↗More from Google
Gemini 3.8 Flash
TextCloud
Google's most capable Flash model, with clear gains over 3.7 Flash in software engineering, agentic tasks, and multi-step reasoning, plus vision and a 1M-token context window.
Gemini 3.7 Flash
TextCloud
Google's newest Flash workhorse, a more capable successor to 3.6 Flash with stronger software engineering, better document comprehension and more disciplined tool use, at half the price per token.
Gemini 3.6 Flash
TextCloud
Google's most efficient multimodal Flash model: an updated reasoning stack with stronger coding and computer-use quality, at the same speed and scale as the rest of the Flash line.
Gemini 3.1 Pro
TextCloud
Google's most capable multimodal model with deep reasoning and 1M token context.
Nano Banana 2
ImageCloud
Ultra-fast image generation model optimised for speed and creative output.
Nano Banana 2 Lite
ImageCloud
Google's fastest, most cost-efficient Nano Banana model — 1K images in ~4 seconds for high-volume workflows.
From the blog
Run Gemma 4 locally: Google's open family, now under a plain license
August 20, 2026Google's strongest open models dropped the custom license for plain Apache 2.0. Five sizes, one command each, phone to workstation.
Google Gemma, explained: which model is for what
June 16, 2026Type “gemma” into your runtime and you get a wall of models: a phone-sized one, a workstation one, and odd cousins. Here’s which one you actually want.
Run GPT-4 class models on your laptop without sending a single byte to the cloud
May 5, 2026Open weights now match GPT-4 quality. Here's how CSuite runs them on your machine: no proxy, no logging, no tokens billed.