InternVL3-38B-hf
OpenGVLab's InternVL3-38B-hf packs 38 billion parameters into a image-generation model. InternVL3-38B-hf is an open-weights image model with roughly 38 billion parameters.
by OpenGVLab · 38B parameters
Best for
Ways to use InternVL3-38B-hf in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your OpenGVLab API key. osFoundry discovers InternVL3-38B-hf 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
InternVL3-38B-hf 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 InternVL3-38B-hf
InternVL3-38B-hf runs on a 24GB consumer or workstation GPU (~23 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~92 GB).
InternVL3-38B-hf vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about InternVL3-38B-hf
Is InternVL3-38B-hf free to use?
InternVL3-38B-hf 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 InternVL3-38B-hf 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 InternVL3-38B-hf need?
Approximately 23 GB at Q4 quantisation, or 92 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run InternVL3-38B-hf locally?
Yes. InternVL3-38B-hf is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is InternVL3-38B-hf best at?
InternVL3-38B-hf is well-suited to image text to text.
How do I use InternVL3-38B-hf in osFoundry?
Paste your OpenGVLab API key in the key dialog (or deploy the open weights for self-hostable models), assign InternVL3-38B-hf to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by OpenGVLab on April 18, 2025. Source: https://huggingface.co/OpenGVLab/InternVL3-38B-hf