作者： Jakub Rusinowski · 最后更新： 2026年9月6日
The first mainstream omni-modal open model that a single consumer GPU can actually hold: text, image, speech and video in, text out, at 3B active parameters from a 30B MoE. 260K context under the NVIDIA Open Model License, which permits commercial use. The efficiency ratio here is the story — video understanding at roughly the per-token cost of a 3B dense model.
| Licence | What it permits | Applies to |
|---|---|---|
NVIDIA Open Model License | Commercial use permitted Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms. | Nemotron 3 Nano Omni 30B-A3B |
| Nemotron 3 Nano Omni 30B-A3B | Min 19 GB VRAM · Q4_K_M · 260,000 ctx · |
The cheapest GPU that runs Nemotron 3 Nano Omni locally (min 19 GB VRAM) is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama then run: ollama run
Minimum VRAM: 19 GB. For best results use Q4_K_M quantization.
Nemotron 3 Nano Omni needs about 19 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nemotron 3 Nano Omni 30B-A3B (19 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Nemotron 3 Nano Omni runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Nemotron 3 Nano Omni in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run . This downloads Nemotron 3 Nano Omni and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.