3b-zh-ft-research_release
3b-zh-ft-research_release is a 3 billion parameter speech-and-audio model from canopylabs, released April 6, 2025. 3b-zh-ft-research_release is an open-weights audio model with roughly 3 billion parameters.
by canopylabs · 3B parameters
Best for
Ways to use 3b-zh-ft-research_release in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your canopylabs API key. osFoundry discovers 3b-zh-ft-research_release 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
3b-zh-ft-research_release 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 3b-zh-ft-research_release
3b-zh-ft-research_release runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~8 GB).
3b-zh-ft-research_release vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 3b-zh-ft-research_release
Is 3b-zh-ft-research_release free to use?
3b-zh-ft-research_release 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 3b-zh-ft-research_release 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 3b-zh-ft-research_release need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run 3b-zh-ft-research_release locally?
Yes. 3b-zh-ft-research_release is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 3b-zh-ft-research_release best at?
3b-zh-ft-research_release is well-suited to text to speech.
How do I use 3b-zh-ft-research_release in osFoundry?
Paste your canopylabs API key in the key dialog (or deploy the open weights for self-hostable models), assign 3b-zh-ft-research_release to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by canopylabs on April 6, 2025. Source: https://huggingface.co/canopylabs/3b-zh-ft-research_release