spatialvla-4b-224-sft-bridge
Released by IPEC-COMMUNITY in 2025, spatialvla-4b-224-sft-bridge is a 4 billion parameter chat model. spatialvla-4b-224-sft-bridge is an open-weights chat model with roughly 4 billion parameters.
by IPEC-COMMUNITY · 4B parameters
Best for
Ways to use spatialvla-4b-224-sft-bridge in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your IPEC-COMMUNITY API key. osFoundry discovers spatialvla-4b-224-sft-bridge 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
spatialvla-4b-224-sft-bridge 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 spatialvla-4b-224-sft-bridge
spatialvla-4b-224-sft-bridge runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
spatialvla-4b-224-sft-bridge vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about spatialvla-4b-224-sft-bridge
Is spatialvla-4b-224-sft-bridge free to use?
spatialvla-4b-224-sft-bridge 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 spatialvla-4b-224-sft-bridge 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 spatialvla-4b-224-sft-bridge need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run spatialvla-4b-224-sft-bridge locally?
Yes. spatialvla-4b-224-sft-bridge is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is spatialvla-4b-224-sft-bridge best at?
spatialvla-4b-224-sft-bridge is well-suited to robotics.
How do I use spatialvla-4b-224-sft-bridge in osFoundry?
Paste your IPEC-COMMUNITY API key in the key dialog (or deploy the open weights for self-hostable models), assign spatialvla-4b-224-sft-bridge to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by IPEC-COMMUNITY on March 16, 2025. Source: https://huggingface.co/IPEC-COMMUNITY/spatialvla-4b-224-sft-bridge