ERNIE-4.5-VL-424B-A47B-PT
Built by baidu, ERNIE-4.5-VL-424B-A47B-PT is a 424 billion parameter image-generation model. ERNIE-4.5-VL-424B-A47B-PT is an open-weights image model with roughly 424 billion parameters.
by baidu · 424B parameters
Best for
Ways to use ERNIE-4.5-VL-424B-A47B-PT in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your baidu API key. osFoundry discovers ERNIE-4.5-VL-424B-A47B-PT 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
ERNIE-4.5-VL-424B-A47B-PT 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.
Use ERNIE-4.5-VL-424B-A47B-PT via API
ERNIE-4.5-VL-424B-A47B-PT is also served by hosted API providers — use it via API (BYOK) if you would rather not manage GPUs. That page lists per-provider pricing.
What hardware can run ERNIE-4.5-VL-424B-A47B-PT
ERNIE-4.5-VL-424B-A47B-PT runs on a multi-GPU setup or H200 141GB at Q4 (~255 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~1018 GB).
ERNIE-4.5-VL-424B-A47B-PT vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about ERNIE-4.5-VL-424B-A47B-PT
Is ERNIE-4.5-VL-424B-A47B-PT free to use?
ERNIE-4.5-VL-424B-A47B-PT 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 ERNIE-4.5-VL-424B-A47B-PT 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 ERNIE-4.5-VL-424B-A47B-PT need?
Approximately 255 GB at Q4 quantisation, or 1018 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run ERNIE-4.5-VL-424B-A47B-PT locally?
Yes. ERNIE-4.5-VL-424B-A47B-PT is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is ERNIE-4.5-VL-424B-A47B-PT best at?
ERNIE-4.5-VL-424B-A47B-PT is well-suited to image text to text.
How do I use ERNIE-4.5-VL-424B-A47B-PT in osFoundry?
Paste your baidu API key in the key dialog (or deploy the open weights for self-hostable models), assign ERNIE-4.5-VL-424B-A47B-PT to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by baidu on June 28, 2025. Source: https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT