Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
NVIDIA's 120B open Mixture-of-Experts, activating just 12B parameters per token for compute efficiency on multi-agent workloads. Like the rest of the Nemotron line it generates a reasoning trace before its final answer, and NVIDIA publishes open weights alongside training data and recipes rather than weights alone. Positioned for collaborative agents and high-volume automation such as IT ticket triage. First-party Ollama tags exist at Q4_K_M, Q8_0 and BF16, so this is genuinely self-hostable — on a multi-GPU box rather than a laptop.
| 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 Super 120B-A12B |
| Nemotron 3 Super 120B-A12B | Min 73 GB VRAM · Q4_K_M · 128,000 ctx · ollama run nemotron-3-super:120b-a12b |
The cheapest GPU that runs Nemotron 3 Super locally (min 73 GB VRAM) is the AMD Ryzen AI Max+ 395 (96 GB).
Install Ollama then run: ollama run nemotron-3-super:120b-a12b
Minimum VRAM: 73 GB. For best results use Q4_K_M quantization.
Nemotron 3 Super needs about 73 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nemotron 3 Super 120B-A12B (73 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Nemotron 3 Super's smallest variant needs about 73 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
Q4_K_M is the best balance of quality and VRAM for Nemotron 3 Super 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 nemotron-3-super:120b-a12b. This downloads Nemotron 3 Super and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.