medgemma3-thinking
medgemma3-thinking is a image-generation model from Testament200156, released September 8, 2025. medgemma3-thinking is an open-weights image model.
by Testament200156
Best for
Ways to use medgemma3-thinking in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Testament200156 API key. osFoundry discovers medgemma3-thinking 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
medgemma3-thinking 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.
medgemma3-thinking vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about medgemma3-thinking
Is medgemma3-thinking free to use?
medgemma3-thinking 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 medgemma3-thinking commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run medgemma3-thinking locally?
Yes. medgemma3-thinking is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is medgemma3-thinking best at?
medgemma3-thinking is well-suited to image text to text.
How do I use medgemma3-thinking in osFoundry?
Paste your Testament200156 API key in the key dialog (or deploy the open weights for self-hostable models), assign medgemma3-thinking to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Testament200156 on September 8, 2025. Source: https://huggingface.co/Testament200156/medgemma3-thinking