visionOCR-3B-061125
Released by prithivMLmods in 2025, visionOCR-3B-061125 is a 3 billion parameter image-generation model. visionOCR-3B-061125 is an open-weights image model with roughly 3 billion parameters.
by prithivMLmods · 3B parameters
Best for
Ways to use visionOCR-3B-061125 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your prithivMLmods API key. osFoundry discovers visionOCR-3B-061125 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
visionOCR-3B-061125 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 visionOCR-3B-061125
visionOCR-3B-061125 runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~8 GB).
visionOCR-3B-061125 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about visionOCR-3B-061125
Is visionOCR-3B-061125 free to use?
visionOCR-3B-061125 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 visionOCR-3B-061125 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 visionOCR-3B-061125 need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run visionOCR-3B-061125 locally?
Yes. visionOCR-3B-061125 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is visionOCR-3B-061125 best at?
visionOCR-3B-061125 is well-suited to image text to text.
How do I use visionOCR-3B-061125 in osFoundry?
Paste your prithivMLmods API key in the key dialog (or deploy the open weights for self-hostable models), assign visionOCR-3B-061125 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by prithivMLmods on June 11, 2025. Source: https://huggingface.co/prithivMLmods/visionOCR-3B-061125