InternVLA-A1-3B-RoboTwin
InternVLA-A1-3B-RoboTwin is a 3 billion parameter chat model from InternRobotics, released January 23, 2026. InternVLA-A1-3B-RoboTwin is an open-weights chat model with roughly 3 billion parameters.
by InternRobotics · 3B parameters
Best for
Ways to use InternVLA-A1-3B-RoboTwin in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your InternRobotics API key. osFoundry discovers InternVLA-A1-3B-RoboTwin 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
InternVLA-A1-3B-RoboTwin 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 InternVLA-A1-3B-RoboTwin
InternVLA-A1-3B-RoboTwin 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).
InternVLA-A1-3B-RoboTwin vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about InternVLA-A1-3B-RoboTwin
Is InternVLA-A1-3B-RoboTwin free to use?
InternVLA-A1-3B-RoboTwin 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 InternVLA-A1-3B-RoboTwin 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 InternVLA-A1-3B-RoboTwin need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run InternVLA-A1-3B-RoboTwin locally?
Yes. InternVLA-A1-3B-RoboTwin is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is InternVLA-A1-3B-RoboTwin best at?
InternVLA-A1-3B-RoboTwin is well-suited to robotics.
How do I use InternVLA-A1-3B-RoboTwin in osFoundry?
Paste your InternRobotics API key in the key dialog (or deploy the open weights for self-hostable models), assign InternVLA-A1-3B-RoboTwin to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by InternRobotics on January 23, 2026. Source: https://huggingface.co/InternRobotics/InternVLA-A1-3B-RoboTwin