Vintern-1B-v3_5
5CD-AI's Vintern-1B-v3_5 packs 1 billion parameters into a image-generation model. Vintern-1B-v3_5 is an open-weights image model with roughly 1 billion parameters.
by 5CD-AI · 1B parameters
Best for
Ways to use Vintern-1B-v3_5 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your 5CD-AI API key. osFoundry discovers Vintern-1B-v3_5 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
Vintern-1B-v3_5 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 Vintern-1B-v3_5
Vintern-1B-v3_5 runs on a single 16GB consumer GPU (~1 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~3 GB).
Vintern-1B-v3_5 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Vintern-1B-v3_5
Is Vintern-1B-v3_5 free to use?
Vintern-1B-v3_5 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 Vintern-1B-v3_5 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 Vintern-1B-v3_5 need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Vintern-1B-v3_5 locally?
Yes. Vintern-1B-v3_5 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Vintern-1B-v3_5 best at?
Vintern-1B-v3_5 is well-suited to image text to text.
How do I use Vintern-1B-v3_5 in osFoundry?
Paste your 5CD-AI API key in the key dialog (or deploy the open weights for self-hostable models), assign Vintern-1B-v3_5 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by 5CD-AI on January 11, 2025. Source: https://huggingface.co/5CD-AI/Vintern-1B-v3_5