Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE
Released by majentik in 2026, Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE is a 30 billion parameter image-generation model. Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE is an open-weights image model with roughly 30 billion parameters.
by majentik · 30B parameters
Best for
Ways to use Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your majentik API key. osFoundry discovers Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE 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
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE 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 Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE 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).
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE
Is Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE free to use?
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE 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 Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE 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 Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE need?
Approximately 18 GB at Q4 quantisation, or 72 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE locally?
Yes. Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE best at?
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE is well-suited to image text to text.
How do I use Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE in osFoundry?
Paste your majentik API key in the key dialog (or deploy the open weights for self-hostable models), assign Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by majentik on May 4, 2026. Source: https://huggingface.co/majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-MXFP4_MOE