MR_MARTIN_31b_V1.0_Gemma-4-base-ftp
Built by ZERO-POINT-AI, MR_MARTIN_31b_V1.0_Gemma-4-base-ftp is an image-generation model. MR_MARTIN_31b_V1.0_Gemma-4-base-ftp is an open-weights image model.
by ZERO-POINT-AI
Best for
Ways to use MR_MARTIN_31b_V1.0_Gemma-4-base-ftp in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ZERO-POINT-AI API key. osFoundry discovers MR_MARTIN_31b_V1.0_Gemma-4-base-ftp 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
MR_MARTIN_31b_V1.0_Gemma-4-base-ftp 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.
MR_MARTIN_31b_V1.0_Gemma-4-base-ftp vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about MR_MARTIN_31b_V1.0_Gemma-4-base-ftp
Is MR_MARTIN_31b_V1.0_Gemma-4-base-ftp free to use?
MR_MARTIN_31b_V1.0_Gemma-4-base-ftp 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 MR_MARTIN_31b_V1.0_Gemma-4-base-ftp 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 MR_MARTIN_31b_V1.0_Gemma-4-base-ftp locally?
Yes. MR_MARTIN_31b_V1.0_Gemma-4-base-ftp is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is MR_MARTIN_31b_V1.0_Gemma-4-base-ftp best at?
MR_MARTIN_31b_V1.0_Gemma-4-base-ftp is well-suited to image text to text.
How do I use MR_MARTIN_31b_V1.0_Gemma-4-base-ftp in osFoundry?
Paste your ZERO-POINT-AI API key in the key dialog (or deploy the open weights for self-hostable models), assign MR_MARTIN_31b_V1.0_Gemma-4-base-ftp to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ZERO-POINT-AI on April 12, 2026. Source: https://huggingface.co/ZERO-POINT-AI/MR_MARTIN_31b_V1.0_Gemma-4-base-ftp