0GM-1.0-35B-A3B-0427
0GM-1.0-35B-A3B-0427 is a 35 billion parameter image-generation model from 0G-AI, released April 27, 2026. 0GM-1.0-35B-A3B-0427 is an open-weights image model with roughly 35 billion parameters.
by 0G-AI · 35B parameters
Best for
Ways to use 0GM-1.0-35B-A3B-0427 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your 0G-AI API key. osFoundry discovers 0GM-1.0-35B-A3B-0427 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
0GM-1.0-35B-A3B-0427 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 0GM-1.0-35B-A3B-0427
0GM-1.0-35B-A3B-0427 runs on a 24GB consumer or workstation GPU (~21 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~84 GB).
0GM-1.0-35B-A3B-0427 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 0GM-1.0-35B-A3B-0427
Is 0GM-1.0-35B-A3B-0427 free to use?
0GM-1.0-35B-A3B-0427 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 0GM-1.0-35B-A3B-0427 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 0GM-1.0-35B-A3B-0427 need?
Approximately 21 GB at Q4 quantisation, or 84 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run 0GM-1.0-35B-A3B-0427 locally?
Yes. 0GM-1.0-35B-A3B-0427 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 0GM-1.0-35B-A3B-0427 best at?
0GM-1.0-35B-A3B-0427 is well-suited to image text to text.
How do I use 0GM-1.0-35B-A3B-0427 in osFoundry?
Paste your 0G-AI API key in the key dialog (or deploy the open weights for self-hostable models), assign 0GM-1.0-35B-A3B-0427 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by 0G-AI on April 27, 2026. Source: https://huggingface.co/0G-AI/0GM-1.0-35B-A3B-0427