PaDT_Pro_3B
PaDT-MLLM's PaDT_Pro_3B packs 3 billion parameters into a chat model. PaDT_Pro_3B is an open-weights chat model with roughly 3 billion parameters.
by PaDT-MLLM · 3B parameters
Best for
Ways to use PaDT_Pro_3B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your PaDT-MLLM API key. osFoundry discovers PaDT_Pro_3B 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
PaDT_Pro_3B 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 PaDT_Pro_3B
PaDT_Pro_3B 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).
PaDT_Pro_3B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about PaDT_Pro_3B
Is PaDT_Pro_3B free to use?
PaDT_Pro_3B 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 PaDT_Pro_3B 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 PaDT_Pro_3B need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run PaDT_Pro_3B locally?
Yes. PaDT_Pro_3B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is PaDT_Pro_3B best at?
PaDT_Pro_3B is well-suited to any to any.
How do I use PaDT_Pro_3B in osFoundry?
Paste your PaDT-MLLM API key in the key dialog (or deploy the open weights for self-hostable models), assign PaDT_Pro_3B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by PaDT-MLLM on October 1, 2025. Source: https://huggingface.co/PaDT-MLLM/PaDT_Pro_3B