Wan2.1-I2V-14B-480P-FP8FakeQuant
Wan2.1-I2V-14B-480P-FP8FakeQuant (AaronHuangWei, 2026) is a 14 billion parameter image-generation model. Wan2.1-I2V-14B-480P-FP8FakeQuant is an open-weights image model with roughly 14 billion parameters.
by AaronHuangWei · 14B parameters
Best for
Ways to use Wan2.1-I2V-14B-480P-FP8FakeQuant in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your AaronHuangWei API key. osFoundry discovers Wan2.1-I2V-14B-480P-FP8FakeQuant 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
Wan2.1-I2V-14B-480P-FP8FakeQuant 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 Wan2.1-I2V-14B-480P-FP8FakeQuant
Wan2.1-I2V-14B-480P-FP8FakeQuant runs on a single 16GB consumer GPU (~9 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~34 GB).
Wan2.1-I2V-14B-480P-FP8FakeQuant vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Wan2.1-I2V-14B-480P-FP8FakeQuant
Is Wan2.1-I2V-14B-480P-FP8FakeQuant free to use?
Wan2.1-I2V-14B-480P-FP8FakeQuant 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 Wan2.1-I2V-14B-480P-FP8FakeQuant 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 Wan2.1-I2V-14B-480P-FP8FakeQuant need?
Approximately 9 GB at Q4 quantisation, or 34 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Wan2.1-I2V-14B-480P-FP8FakeQuant locally?
Yes. Wan2.1-I2V-14B-480P-FP8FakeQuant is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Wan2.1-I2V-14B-480P-FP8FakeQuant best at?
Wan2.1-I2V-14B-480P-FP8FakeQuant is well-suited to image to video.
How do I use Wan2.1-I2V-14B-480P-FP8FakeQuant in osFoundry?
Paste your AaronHuangWei API key in the key dialog (or deploy the open weights for self-hostable models), assign Wan2.1-I2V-14B-480P-FP8FakeQuant to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by AaronHuangWei on January 4, 2026. Source: https://huggingface.co/AaronHuangWei/Wan2.1-I2V-14B-480P-FP8FakeQuant