NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e
Built by splats, NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e is a 30 billion parameter chat model. NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e is an open-weights chat model with roughly 30 billion parameters.
by splats · 30B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your splats API key. osFoundry discovers NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e 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
NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e 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 NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e
NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e runs on a 24GB consumer or workstation GPU (~18 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~72 GB).
NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e
Is NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e free to use?
NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e 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 NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e 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 NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e need?
Approximately 18 GB at Q4 quantisation, or 72 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e locally?
Yes. NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e best at?
NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e in osFoundry?
Paste your splats API key in the key dialog (or deploy the open weights for self-hostable models), assign NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by splats on April 27, 2026. Source: https://huggingface.co/splats/NVIDIA-Nemotron-3-Nano-30B-A3B-oQ4e