luau-coder-preview-28B-A3B-noft
luau-coder-preview-28B-A3B-noft is a 28 billion parameter chat model from khtsly, released April 26, 2026. luau-coder-preview-28B-A3B-noft is an open-weights chat model with roughly 28 billion parameters.
by khtsly · 28B parameters
Best for
Ways to use luau-coder-preview-28B-A3B-noft in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your khtsly API key. osFoundry discovers luau-coder-preview-28B-A3B-noft 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
luau-coder-preview-28B-A3B-noft 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 luau-coder-preview-28B-A3B-noft
luau-coder-preview-28B-A3B-noft runs on a 24GB consumer or workstation GPU (~17 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~68 GB).
luau-coder-preview-28B-A3B-noft vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about luau-coder-preview-28B-A3B-noft
Is luau-coder-preview-28B-A3B-noft free to use?
luau-coder-preview-28B-A3B-noft 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 luau-coder-preview-28B-A3B-noft 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 luau-coder-preview-28B-A3B-noft need?
Approximately 17 GB at Q4 quantisation, or 68 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run luau-coder-preview-28B-A3B-noft locally?
Yes. luau-coder-preview-28B-A3B-noft is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is luau-coder-preview-28B-A3B-noft best at?
luau-coder-preview-28B-A3B-noft is well-suited to text generation.
How do I use luau-coder-preview-28B-A3B-noft in osFoundry?
Paste your khtsly API key in the key dialog (or deploy the open weights for self-hostable models), assign luau-coder-preview-28B-A3B-noft to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by khtsly on April 26, 2026. Source: https://huggingface.co/khtsly/luau-coder-preview-28B-A3B-noft