Qwen2.5-VL-72B-Instruct-3bit
Qwen2.5-VL-72B-Instruct-3bit (mlx-community, 2025) is a 72 billion parameter image-generation model. Qwen2.5-VL-72B-Instruct-3bit is an open-weights image model with roughly 72 billion parameters.
by mlx-community · 72B parameters
Best for
Ways to use Qwen2.5-VL-72B-Instruct-3bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mlx-community API key. osFoundry discovers Qwen2.5-VL-72B-Instruct-3bit 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
Qwen2.5-VL-72B-Instruct-3bit 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 Qwen2.5-VL-72B-Instruct-3bit
Qwen2.5-VL-72B-Instruct-3bit runs on a single A100 80GB or H100 80GB at Q4 quantisation (~44 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~173 GB).
Qwen2.5-VL-72B-Instruct-3bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen2.5-VL-72B-Instruct-3bit
Is Qwen2.5-VL-72B-Instruct-3bit free to use?
Qwen2.5-VL-72B-Instruct-3bit 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 Qwen2.5-VL-72B-Instruct-3bit 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 Qwen2.5-VL-72B-Instruct-3bit need?
Approximately 44 GB at Q4 quantisation, or 173 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Qwen2.5-VL-72B-Instruct-3bit locally?
Yes. Qwen2.5-VL-72B-Instruct-3bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen2.5-VL-72B-Instruct-3bit best at?
Qwen2.5-VL-72B-Instruct-3bit is well-suited to image text to text.
How do I use Qwen2.5-VL-72B-Instruct-3bit in osFoundry?
Paste your mlx-community API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen2.5-VL-72B-Instruct-3bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mlx-community on January 29, 2025. Source: https://huggingface.co/mlx-community/Qwen2.5-VL-72B-Instruct-3bit