K82
K82 is a chat model from Mhair, released September 12, 2025. K82 is an open-weights chat model.
by Mhair
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use K82 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Mhair API key. osFoundry discovers K82 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
K82 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.
K82 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about K82
Is K82 free to use?
K82 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 K82 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 K82 locally?
Yes. K82 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is K82 best at?
K82 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use K82 in osFoundry?
Paste your Mhair API key in the key dialog (or deploy the open weights for self-hostable models), assign K82 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Mhair on September 12, 2025. Source: https://huggingface.co/Mhair/K82