InternVL2_5-26B
OpenGVLab's InternVL2_5-26B packs 26 billion parameters into a image-generation model. InternVL2_5-26B is an open-weights image model with roughly 26 billion parameters.
by OpenGVLab · 26B parameters
Best for
Ways to use InternVL2_5-26B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your OpenGVLab API key. osFoundry discovers InternVL2_5-26B 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
InternVL2_5-26B 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 InternVL2_5-26B
InternVL2_5-26B runs on a single 16GB consumer GPU (~16 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~63 GB).
InternVL2_5-26B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about InternVL2_5-26B
Is InternVL2_5-26B free to use?
InternVL2_5-26B 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 InternVL2_5-26B 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 InternVL2_5-26B need?
Approximately 16 GB at Q4 quantisation, or 63 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run InternVL2_5-26B locally?
Yes. InternVL2_5-26B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is InternVL2_5-26B best at?
InternVL2_5-26B is well-suited to image text to text.
How do I use InternVL2_5-26B in osFoundry?
Paste your OpenGVLab API key in the key dialog (or deploy the open weights for self-hostable models), assign InternVL2_5-26B 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 November 20, 2024. Source: https://huggingface.co/OpenGVLab/InternVL2_5-26B