gemma-4-26B-A4B
Released by google in 2026, gemma-4-26B-A4B is a 26 billion parameter image-generation model. gemma-4-26B-A4B is an open-weights image model with roughly 26 billion parameters.
by google · 26B parameters
Best for
Ways to use gemma-4-26B-A4B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your google API key. osFoundry discovers gemma-4-26B-A4B automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
gemma-4-26B-A4B is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run gemma-4-26B-A4B
gemma-4-26B-A4B runs on a single 16GB consumer GPU (~16 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~63 GB).
gemma-4-26B-A4B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gemma-4-26B-A4B
Is gemma-4-26B-A4B free to use?
gemma-4-26B-A4B is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use gemma-4-26B-A4B commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does gemma-4-26B-A4B need?
Approximately 16 GB at Q4 quantisation, or 63 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-4-26B-A4B locally?
Yes. gemma-4-26B-A4B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-4-26B-A4B best at?
gemma-4-26B-A4B is well-suited to image text to text.
How do I use gemma-4-26B-A4B in osFoundry?
Paste your google API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-4-26B-A4B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by google on March 12, 2026. Source: https://huggingface.co/google/gemma-4-26B-A4B