wan22-t2v-a14b-modelopt-fp8-sglang-transformer
BBuf's wan22-t2v-a14b-modelopt-fp8-sglang-transformer packs 14 billion parameters into a chat model. wan22-t2v-a14b-modelopt-fp8-sglang-transformer is an open-weights chat model with roughly 14 billion parameters.
by BBuf · 14B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use wan22-t2v-a14b-modelopt-fp8-sglang-transformer in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your BBuf API key. osFoundry discovers wan22-t2v-a14b-modelopt-fp8-sglang-transformer 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
wan22-t2v-a14b-modelopt-fp8-sglang-transformer 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 wan22-t2v-a14b-modelopt-fp8-sglang-transformer
wan22-t2v-a14b-modelopt-fp8-sglang-transformer 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).
wan22-t2v-a14b-modelopt-fp8-sglang-transformer vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about wan22-t2v-a14b-modelopt-fp8-sglang-transformer
Is wan22-t2v-a14b-modelopt-fp8-sglang-transformer free to use?
wan22-t2v-a14b-modelopt-fp8-sglang-transformer 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 wan22-t2v-a14b-modelopt-fp8-sglang-transformer 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 wan22-t2v-a14b-modelopt-fp8-sglang-transformer need?
Approximately 9 GB at Q4 quantisation, or 34 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run wan22-t2v-a14b-modelopt-fp8-sglang-transformer locally?
Yes. wan22-t2v-a14b-modelopt-fp8-sglang-transformer is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is wan22-t2v-a14b-modelopt-fp8-sglang-transformer best at?
wan22-t2v-a14b-modelopt-fp8-sglang-transformer is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use wan22-t2v-a14b-modelopt-fp8-sglang-transformer in osFoundry?
Paste your BBuf API key in the key dialog (or deploy the open weights for self-hostable models), assign wan22-t2v-a14b-modelopt-fp8-sglang-transformer to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by BBuf on April 8, 2026. Source: https://huggingface.co/BBuf/wan22-t2v-a14b-modelopt-fp8-sglang-transformer