XORTRON.CriminalComputing.2026.27B.Instruct.NEXT
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT is a 2026 billion parameter image-generation model from darkc0de, released April 6, 2026. XORTRON.CriminalComputing.2026.27B.Instruct.NEXT is an open-weights image model with roughly 2026 billion parameters.
by darkc0de · 2026B parameters
Best for
Ways to use XORTRON.CriminalComputing.2026.27B.Instruct.NEXT in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your darkc0de API key. osFoundry discovers XORTRON.CriminalComputing.2026.27B.Instruct.NEXT 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
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT 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 XORTRON.CriminalComputing.2026.27B.Instruct.NEXT
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT runs on a multi-GPU setup or H200 141GB at Q4 (~1216 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~4863 GB).
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about XORTRON.CriminalComputing.2026.27B.Instruct.NEXT
Is XORTRON.CriminalComputing.2026.27B.Instruct.NEXT free to use?
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT 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 XORTRON.CriminalComputing.2026.27B.Instruct.NEXT 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 XORTRON.CriminalComputing.2026.27B.Instruct.NEXT need?
Approximately 1216 GB at Q4 quantisation, or 4863 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run XORTRON.CriminalComputing.2026.27B.Instruct.NEXT locally?
Yes. XORTRON.CriminalComputing.2026.27B.Instruct.NEXT is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is XORTRON.CriminalComputing.2026.27B.Instruct.NEXT best at?
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT is well-suited to image text to text.
How do I use XORTRON.CriminalComputing.2026.27B.Instruct.NEXT in osFoundry?
Paste your darkc0de API key in the key dialog (or deploy the open weights for self-hostable models), assign XORTRON.CriminalComputing.2026.27B.Instruct.NEXT to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by darkc0de on April 6, 2026. Source: https://huggingface.co/darkc0de/XORTRON.CriminalComputing.2026.27B.Instruct.NEXT