Nemotron 3 Super

What Nemotron 3 Super is for

Nemotron 3 Super is a reasoning model: it spends output tokens working through a problem before answering, which makes it slower per useful word and better on problems that need the working shown. NVIDIA released it in 2026-03 with a single 120B (12B active MoE) size under NVIDIA Open Model License, with a 128K context window. Budget for the extra tokens the thinking phase consumes. The catalogue records its strength as maximum compute efficiency for multi-agent workflows.

Sizes and memory

Our catalogue does not carry a per-size memory breakdown for Nemotron 3 Super. What it records instead is a floor of 48 GB and a recommended 96 GB for the default configuration. Until a per-size figure exists, treat those two numbers as the whole guidance rather than reading a size table that would have to be invented.

Hardware that runs Nemotron 3 Super

Without a per-size memory figure there is no honest way to say which card holds Nemotron 3 Super. Its recorded floor of 48 GB rules out every consumer card in our hardware guide, which tops out well below that.

What people use it for

The catalogue lists 4 recorded uses for Nemotron 3 Super: multi-agent, agentic, reasoning, tool use. It is tagged reasoning, thinking, MoE, multi-agent, agentic.

Where Nemotron 3 Super sits in the Nemotron family

Nemotron 3 Super is the only Nemotron entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.

It ships under the NVIDIA Open Model License, which is neither a standard open-source licence nor a closed one. Read the terms before shipping anything commercial on top of it.

Context window: 128K

128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.

How to run Nemotron 3 Super locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for Nemotron 3 Super at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "Nemotron 3 Super GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.