260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32
260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 is a chat model from dreamgonfly, released April 23, 2026. 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 is an open-weights chat model.
by dreamgonfly
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your dreamgonfly API key. osFoundry discovers 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 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
260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 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.
260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32
Is 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 free to use?
260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 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 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 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 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 locally?
Yes. 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 best at?
260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 in osFoundry?
Paste your dreamgonfly API key in the key dialog (or deploy the open weights for self-hostable models), assign 260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by dreamgonfly on April 23, 2026. Source: https://huggingface.co/dreamgonfly/260423_EXAONE-4.0.1-32B_classify-en_lora_step6050_alpha32