eva02_base_patch16_clip_224.merged2b
timm's eva02_base_patch16_clip_224.merged2b packs 2 billion parameters into a image-generation model. eva02_base_patch16_clip_224.merged2b is an open-weights image model with roughly 2 billion parameters.
by timm · 2B parameters
Best for
- zero shot image classification
Ways to use eva02_base_patch16_clip_224.merged2b in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your timm API key. osFoundry discovers eva02_base_patch16_clip_224.merged2b 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
eva02_base_patch16_clip_224.merged2b 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 eva02_base_patch16_clip_224.merged2b
eva02_base_patch16_clip_224.merged2b 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).
eva02_base_patch16_clip_224.merged2b vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about eva02_base_patch16_clip_224.merged2b
Is eva02_base_patch16_clip_224.merged2b free to use?
eva02_base_patch16_clip_224.merged2b 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 eva02_base_patch16_clip_224.merged2b 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 eva02_base_patch16_clip_224.merged2b need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run eva02_base_patch16_clip_224.merged2b locally?
Yes. eva02_base_patch16_clip_224.merged2b is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is eva02_base_patch16_clip_224.merged2b best at?
eva02_base_patch16_clip_224.merged2b is well-suited to zero shot image classification.
How do I use eva02_base_patch16_clip_224.merged2b in osFoundry?
Paste your timm API key in the key dialog (or deploy the open weights for self-hostable models), assign eva02_base_patch16_clip_224.merged2b to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by timm on December 26, 2024. Source: https://huggingface.co/timm/eva02_base_patch16_clip_224.merged2b