EvoCUA-32B-20260105
EvoCUA-32B-20260105 is a 32 billion parameter chat model from meituan, released January 7, 2026. EvoCUA-32B-20260105 is an open-weights chat model with roughly 32 billion parameters.
by meituan · 32B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use EvoCUA-32B-20260105 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your meituan API key. osFoundry discovers EvoCUA-32B-20260105 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
EvoCUA-32B-20260105 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 EvoCUA-32B-20260105
EvoCUA-32B-20260105 runs on a 24GB consumer or workstation GPU (~20 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~77 GB).
EvoCUA-32B-20260105 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about EvoCUA-32B-20260105
Is EvoCUA-32B-20260105 free to use?
EvoCUA-32B-20260105 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 EvoCUA-32B-20260105 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 EvoCUA-32B-20260105 need?
Approximately 20 GB at Q4 quantisation, or 77 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run EvoCUA-32B-20260105 locally?
Yes. EvoCUA-32B-20260105 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is EvoCUA-32B-20260105 best at?
EvoCUA-32B-20260105 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use EvoCUA-32B-20260105 in osFoundry?
Paste your meituan API key in the key dialog (or deploy the open weights for self-hostable models), assign EvoCUA-32B-20260105 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by meituan on January 7, 2026. Source: https://huggingface.co/meituan/EvoCUA-32B-20260105