AquilaChat2-34B
BAAI's AquilaChat2-34B packs 34 billion parameters into a chat model. AquilaChat2-34B is an open-weights chat model with roughly 34 billion parameters.
by BAAI · 34B parameters
Best for
Ways to use AquilaChat2-34B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your BAAI API key. osFoundry discovers AquilaChat2-34B 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
AquilaChat2-34B 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 AquilaChat2-34B
AquilaChat2-34B runs on a 24GB consumer or workstation GPU (~21 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~82 GB).
AquilaChat2-34B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about AquilaChat2-34B
Is AquilaChat2-34B free to use?
AquilaChat2-34B 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 AquilaChat2-34B 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 AquilaChat2-34B need?
Approximately 21 GB at Q4 quantisation, or 82 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run AquilaChat2-34B locally?
Yes. AquilaChat2-34B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is AquilaChat2-34B best at?
AquilaChat2-34B is well-suited to text generation.
How do I use AquilaChat2-34B in osFoundry?
Paste your BAAI API key in the key dialog (or deploy the open weights for self-hostable models), assign AquilaChat2-34B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by BAAI on October 11, 2023. Source: https://huggingface.co/BAAI/AquilaChat2-34B