BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Nemotron 3 Super 120B

By NVIDIA · United States

Updated 2026-07-13

chat general reasoning moe
Parameters
120B
License
NVIDIA Open Model License
Context
125k
VRAM (Q4)
72 GB
Released
March 2026

Overview

NVIDIA's first frontier-class release, a 120B MoE with 12B active parameters scoring 60% on SWE-Bench Verified. Ships with the 10T-token training corpus.

When to pick this model

  • Enterprise deployments needing NVIDIA's commercial license
  • SWE-Bench-grade coding agents on a multi-GPU rig
  • Long-context analysis up to 128K tokens
  • Reproducible research using the released training data
  • Replacing closed APIs with NVIDIA-backed weights

VRAM requirements by quantization

VRAM REQUIRED (GB)24324880128Q4_K_M72 GBQ5_K_M86 GBQ8_0132 GBFP16240 GB
QuantizationVRAM required
Q4_K_M (recommended)72 GB
Q5_K_M86 GB
Q8_0132 GB
FP16 (no quantization)240 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, Nemotron 3 Super 120B is server-class even at Q4_K_M (72 GB). Stepping up to Q8_0 nearly doubles the footprint to 132 GB, and unquantized FP16 weights take 240 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, Nemotron 3 Super 120B needs roughly 100 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 2 tokens/sec on entry-level GPUs, on the order of 10 tokens/sec on a mid-range card, and up to 25 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches Nemotron 3 Super 120B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for Nemotron 3 Super 120B
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBDoes not fit — needs 72 GB at Q4_K_M
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopDoes not fit — needs 72 GB at Q4_K_M
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTDoes not fit — needs 72 GB at Q4_K_M
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopDoes not fit — needs 72 GB at Q4_K_M
32 GBRTX 5090Does not fit — needs 72 GB at Q4_K_M

Which GPU should you buy to run Nemotron 3 Super 120B?

To run Nemotron 3 Super 120B locally at Q4, you need ~72 GB of VRAM. The best value for this is a Apple Mac Studio (64+ GB unified memory).

Check Apple Mac Studio price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Published benchmark scores

BenchmarkScore
SWE-Bench Verified60

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

  • NVIDIA's first true frontier open release
  • 60% on SWE-Bench Verified
  • Commercially permissive NVIDIA Open Model License
  • 10T-token training corpus released alongside weights

Limitations

  • 72GB+ in Q4 needs serious hardware
  • Ollama support is still partial
  • License is permissive but not Apache 2.0

Typical workloads

In our catalog grid, Nemotron 3 Super 120B is filed under Enterprise, Agents, Code — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multi-step reasoning and math-flavoured tasks.

The 125k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. It ships under the NVIDIA Open Model License license — commercial use is generally possible but read the specific terms before embedding it in a product.

Architecture & training

Architecture: MoE 120B/12B active · NVIDIA Open Model License

Training: 10T training tokens also released.

Verdict

A credible NVIDIA-backed frontier model with the rare bonus of a public training corpus.

Quick start

ollama run nemotron-3-super:120b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does Nemotron 3 Super 120B need?

At the recommended Q4_K_M quantization, Nemotron 3 Super 120B needs about 72 GB of VRAM. Q8_0 takes 132 GB, and unquantized FP16 weights take 240 GB.

Can Nemotron 3 Super 120B run without a GPU?

Yes — with roughly 100 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does Nemotron 3 Super 120B support?

Nemotron 3 Super 120B supports a 125k-token context window (128,000 tokens).

Can I use Nemotron 3 Super 120B commercially?

Nemotron 3 Super 120B ships under the NVIDIA Open Model License license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.

How fast is Nemotron 3 Super 120B on consumer hardware?

Our compatibility engine estimates on the order of 10 tokens/sec on a mid-range GPU and up to 25 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of Nemotron 3 Super 120B should I download first?

Start with Q4_K_M (72 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It does not fit a single 24 GB consumer card — plan for multi-GPU or server hardware.

Tools

Is Nemotron 3 Super 120B the right pick for you?

Compute self-hosted ROI → Back to catalog