Holotron-12B
Holotron-12B is a 12 billion parameter image-generation model from Hcompany, released February 6, 2026. Holotron-12B is an open-weights image model with roughly 12 billion parameters.
by Hcompany · 12B parameters
Best for
Ways to use Holotron-12B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Hcompany API key. osFoundry discovers Holotron-12B 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
Holotron-12B 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 Holotron-12B
Holotron-12B runs on a single 16GB consumer GPU (~8 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~29 GB).
Holotron-12B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Holotron-12B
Is Holotron-12B free to use?
Holotron-12B 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 Holotron-12B 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 Holotron-12B need?
Approximately 8 GB at Q4 quantisation, or 29 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Holotron-12B locally?
Yes. Holotron-12B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Holotron-12B best at?
Holotron-12B is well-suited to image text to text.
How do I use Holotron-12B in osFoundry?
Paste your Hcompany API key in the key dialog (or deploy the open weights for self-hostable models), assign Holotron-12B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Hcompany on February 6, 2026. Source: https://huggingface.co/Hcompany/Holotron-12B