CLIP-ViT-H-14-laion2B-s32B-b79K
CLIP-ViT-H-14-laion2B-s32B-b79K is a 2 billion parameter image-generation model from jk0125, released April 15, 2026. CLIP-ViT-H-14-laion2B-s32B-b79K is an open-weights image model with roughly 2 billion parameters.
by jk0125 · 2B parameters
Best for
- zero shot image classification
Ways to use CLIP-ViT-H-14-laion2B-s32B-b79K in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your jk0125 API key. osFoundry discovers CLIP-ViT-H-14-laion2B-s32B-b79K 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
CLIP-ViT-H-14-laion2B-s32B-b79K 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 CLIP-ViT-H-14-laion2B-s32B-b79K
CLIP-ViT-H-14-laion2B-s32B-b79K 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 (~5 GB).
CLIP-ViT-H-14-laion2B-s32B-b79K vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about CLIP-ViT-H-14-laion2B-s32B-b79K
Is CLIP-ViT-H-14-laion2B-s32B-b79K free to use?
CLIP-ViT-H-14-laion2B-s32B-b79K 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 CLIP-ViT-H-14-laion2B-s32B-b79K 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 CLIP-ViT-H-14-laion2B-s32B-b79K need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run CLIP-ViT-H-14-laion2B-s32B-b79K locally?
Yes. CLIP-ViT-H-14-laion2B-s32B-b79K is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is CLIP-ViT-H-14-laion2B-s32B-b79K best at?
CLIP-ViT-H-14-laion2B-s32B-b79K is well-suited to zero shot image classification.
How do I use CLIP-ViT-H-14-laion2B-s32B-b79K in osFoundry?
Paste your jk0125 API key in the key dialog (or deploy the open weights for self-hostable models), assign CLIP-ViT-H-14-laion2B-s32B-b79K to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by jk0125 on April 15, 2026. Source: https://huggingface.co/jk0125/CLIP-ViT-H-14-laion2B-s32B-b79K