tiny-random-llama4
Built by optimum-intel-internal-testing, tiny-random-llama4 is an image-generation model. tiny-random-llama4 is an open-weights image model.
by optimum-intel-internal-testing
Best for
Ways to use tiny-random-llama4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your optimum-intel-internal-testing API key. osFoundry discovers tiny-random-llama4 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
tiny-random-llama4 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.
tiny-random-llama4 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| tiny-random-llama4 | optimum-intel-internal-testing | — | — | Free (local) | Yes |
| FLUX.1-Krea-dev | black-forest-labs | — | — | Free (local) | Yes |
| mnasnet_100.rmsp_in1k | timm | — | — | Free (local) | Yes |
| Chroma1-HD | lodestones | — | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about tiny-random-llama4
Is tiny-random-llama4 free to use?
tiny-random-llama4 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 tiny-random-llama4 commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run tiny-random-llama4 locally?
Yes. tiny-random-llama4 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is tiny-random-llama4 best at?
tiny-random-llama4 is well-suited to image text to text.
How do I use tiny-random-llama4 in osFoundry?
Paste your optimum-intel-internal-testing API key in the key dialog (or deploy the open weights for self-hostable models), assign tiny-random-llama4 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by optimum-intel-internal-testing on October 21, 2025. Source: https://huggingface.co/optimum-intel-internal-testing/tiny-random-llama4