ettin-decoder-68m
Released by jhu-clsp in 2025, ettin-decoder-68m is an chat model. ettin-decoder-68m is an open-weights chat model.
by jhu-clsp
Best for
Ways to use ettin-decoder-68m in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your jhu-clsp API key. osFoundry discovers ettin-decoder-68m 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
ettin-decoder-68m 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.
ettin-decoder-68m vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about ettin-decoder-68m
Is ettin-decoder-68m free to use?
ettin-decoder-68m 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 ettin-decoder-68m 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 ettin-decoder-68m locally?
Yes. ettin-decoder-68m is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is ettin-decoder-68m best at?
ettin-decoder-68m is well-suited to fill mask.
How do I use ettin-decoder-68m in osFoundry?
Paste your jhu-clsp API key in the key dialog (or deploy the open weights for self-hostable models), assign ettin-decoder-68m to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by jhu-clsp on July 3, 2025. Source: https://huggingface.co/jhu-clsp/ettin-decoder-68m