NVILA-15B
Released by Efficient-Large-Model in 2024, NVILA-15B is a 15 billion parameter chat model. NVILA-15B is an open-weights chat model with roughly 15 billion parameters.
by Efficient-Large-Model · 15B parameters
Best for
Ways to use NVILA-15B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Efficient-Large-Model API key. osFoundry discovers NVILA-15B 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
NVILA-15B 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 NVILA-15B
NVILA-15B runs on a single 16GB consumer GPU (~9 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~36 GB).
NVILA-15B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about NVILA-15B
Is NVILA-15B free to use?
NVILA-15B 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 NVILA-15B 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 NVILA-15B need?
Approximately 9 GB at Q4 quantisation, or 36 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run NVILA-15B locally?
Yes. NVILA-15B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is NVILA-15B best at?
NVILA-15B is well-suited to text generation.
How do I use NVILA-15B in osFoundry?
Paste your Efficient-Large-Model API key in the key dialog (or deploy the open weights for self-hostable models), assign NVILA-15B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Efficient-Large-Model on December 4, 2024. Source: https://huggingface.co/Efficient-Large-Model/NVILA-15B