Kairos_50m
Kairos_50m is a chat model from mldi-lab, released September 30, 2025. Kairos_50m is an open-weights chat model.
by mldi-lab
Best for
Ways to use Kairos_50m in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mldi-lab API key. osFoundry discovers Kairos_50m 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
Kairos_50m 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.
Kairos_50m vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Kairos_50m | mldi-lab | — | — | Free (local) | Yes |
| mamba2-130m | state-spaces | — | — | Free (local) | Yes |
| Anim4 | Kutches | — | — | Free (local) | Yes |
| CodeFormula | docling-project | — | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Kairos_50m
Is Kairos_50m free to use?
Kairos_50m 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 Kairos_50m commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run Kairos_50m locally?
Yes. Kairos_50m is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Kairos_50m best at?
Kairos_50m is well-suited to time series forecasting.
How do I use Kairos_50m in osFoundry?
Paste your mldi-lab API key in the key dialog (or deploy the open weights for self-hostable models), assign Kairos_50m to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mldi-lab on September 30, 2025. Source: https://huggingface.co/mldi-lab/Kairos_50m