alia-40b-distill-vapol
Released by apol in 2026, alia-40b-distill-vapol is a 40 billion parameter chat model. alia-40b-distill-vapol is an open-weights chat model with roughly 40 billion parameters.
by apol · 40B parameters
Best for
Ways to use alia-40b-distill-vapol in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your apol API key. osFoundry discovers alia-40b-distill-vapol 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
alia-40b-distill-vapol 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 alia-40b-distill-vapol
alia-40b-distill-vapol runs on a 24GB consumer or workstation GPU (~24 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~96 GB).
alia-40b-distill-vapol vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about alia-40b-distill-vapol
Is alia-40b-distill-vapol free to use?
alia-40b-distill-vapol 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 alia-40b-distill-vapol 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 alia-40b-distill-vapol need?
Approximately 24 GB at Q4 quantisation, or 96 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run alia-40b-distill-vapol locally?
Yes. alia-40b-distill-vapol is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is alia-40b-distill-vapol best at?
alia-40b-distill-vapol is well-suited to text generation.
How do I use alia-40b-distill-vapol in osFoundry?
Paste your apol API key in the key dialog (or deploy the open weights for self-hostable models), assign alia-40b-distill-vapol to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by apol on April 28, 2026. Source: https://huggingface.co/apol/alia-40b-distill-vapol