Dia-1.6B-0626
Dia-1.6B-0626 (nari-labs, 2025) is a 2 billion parameter speech-and-audio model. Dia-1.6B-0626 is an open-weights audio model with roughly 2 billion parameters.
by nari-labs · 2B parameters
Best for
Ways to use Dia-1.6B-0626 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your nari-labs API key. osFoundry discovers Dia-1.6B-0626 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
Dia-1.6B-0626 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 Dia-1.6B-0626
Dia-1.6B-0626 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 (~5 GB).
Dia-1.6B-0626 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Dia-1.6B-0626
Is Dia-1.6B-0626 free to use?
Dia-1.6B-0626 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 Dia-1.6B-0626 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 Dia-1.6B-0626 need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Dia-1.6B-0626 locally?
Yes. Dia-1.6B-0626 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Dia-1.6B-0626 best at?
Dia-1.6B-0626 is well-suited to text to speech.
How do I use Dia-1.6B-0626 in osFoundry?
Paste your nari-labs API key in the key dialog (or deploy the open weights for self-hostable models), assign Dia-1.6B-0626 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by nari-labs on June 26, 2025. Source: https://huggingface.co/nari-labs/Dia-1.6B-0626