NVIDIA · nemotron_h_moe
Can I run nemotron-3-super?
NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextnemotron-3-super system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| nemotron-3-super:120b120B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 80.9 GB | ~93.2 GB |
| nemotron-3-super:120b-a12b-q8_0120B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 122.6 GB | ~138.3 GB |
Showing the 2 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run nemotron-3-super locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull nemotron-3-super:120b - 3.Check the source for the build's task. For text generation, run
ollama run nemotron-3-super:120b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about nemotron-3-super
- How much VRAM do I need to run nemotron-3-super?
- At 4K context, the smallest published build of nemotron-3-super (Q4_K_M) needs roughly 93.2 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run nemotron-3-super without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 93.2 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- How big is the nemotron-3-super download?
- The smallest published build is 80.9 GB. There are 2 builds in total, the largest being 122.6 GB. Leave some extra free disk space beyond the download itself.
- How do I run nemotron-3-super locally?
- Install Ollama, then download a specific build with "ollama pull nemotron-3-super:120b". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.
Will nemotron-3-super run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026