Nemotron 3.5 Bolt
Runs on your deviceNVIDIA · Oct 2026
NVIDIA's edge agent model - a 74B mixture-of-experts with 9B active per token, packed into 22 GB at a native 2-bit quantization, with a 256K context and image understanding. Built for local agents on a 24 GB graphics card, or a 32 GB machine with the experts in main memory.
- Context
- 256K tokens
- Smallest download
- 22.0 GB
- Runs from
- 32 GB RAM
- License
- OpenMDW 1.1
Will Nemotron 3.5 Bolt run on your machine?
This is the same sizing the app uses - not a marketing estimate.
Mixture-of-experts: the always-on layers sit on your card, the experts sit in system memory - bigger than your card, still quick.
On Apple Silicon, system memory is also graphics memory - pick "None / integrated / Apple Silicon" and read the bars against your Mac's memory. The app checks your real hardware before every download.
Variants & sizes
| Variant | Download | Quantization | Needs | Apple Silicon |
|---|---|---|---|---|
| 74B-A9B (MoE)MoE | 22.0 GB | IQ2_XXS | 32 GB RAM | Metal (GGUF) |
The app picks the right variant for your machine and verifies every download. Model files come straight from their official repositories, pinned to exact revisions.
Context window, compared
License
Nemotron 3.5 Bolt is released under the OpenMDW 1.1 - read the terms. The weights download to your machine and stay there; Your Own AI adds no accounts, tracking, or lock-in on top.
Frequently asked questions
- Can I run Nemotron 3.5 Bolt offline?
- Yes. Nemotron 3.5 Bolt is a downloadable model: with Your Own AI it runs entirely on your computer, works with no internet connection, and your conversations never leave your device.
- What hardware does Nemotron 3.5 Bolt need?
- The smallest variant (74B-A9B (MoE), a 22.0 GB download) runs on a machine with 32 GB of memory. Larger variants want more memory or a graphics card - the interactive checker on this page grades every variant against your hardware, using the same logic as the app.
- Is Nemotron 3.5 Bolt free to use?
- The model weights are released under the OpenMDW 1.1 license and download at no charge. Your Own AI itself is free and open source for local use.
- How much context does Nemotron 3.5 Bolt support?
- 256K tokens of context.
- Can Nemotron 3.5 Bolt see images?
- Yes - attach screenshots, charts, or documents and it reads them locally. Nothing is uploaded.
Run Nemotron 3.5 Bolt in two clicks
Download Your Own AI, pick Nemotron 3.5 Bolt, and the app sizes it to your hardware. Private by architecture - no account needed for local use.