Open-weight vision-language model
Nemotron 3.5 Bolt
Nemotron 3.5 Bolt 74B-A9B 24GB is an open-weight vision-language model from NVIDIA, released on 15 October 2026. It is a mixture-of-experts model with 74B total and 9B active parameters, compressed from Nemotron 3.5 Super VL and quantized to 2 bits so it fits in 24GB of memory for local AI agents.
Last reviewed 28 Oct 2026 · by NVIDIA
Facts at a glance
| Developer | NVIDIA |
|---|---|
| Released | 15 October 2026 on Hugging Face source |
| Parameters | 74B total, 9B active (mixture of experts) source |
| Context window | Up to 256K tokens source |
| Memory footprint | 24GB packed model, experts at 2.0625 bits per element (IQ2_XXS) source |
| Inputs and outputs | Text, images and video in; text out |
| License | OpenMDW License Agreement 1.1 |
| Post-training data cutoff | May 2026 source |
What Nemotron 3.5 Bolt is used for
NVIDIA built the model for everyday agentic tasks that run locally, such as tool calling, web browsing and terminal use. The architecture is a hybrid of Mamba-2 and Transformer layers with a latent mixture-of-experts design and a C-RADIO v4-H vision encoder. NVIDIA ships a separate LiLiCorr speculative decoding drafter and GGUF files for llama.cpp.
Questions people ask
- When was Nemotron 3.5 Bolt released?
- NVIDIA published the weights on Hugging Face on 15 October 2026.
- How much memory does Nemotron 3.5 Bolt need?
- NVIDIA says the packed model fits in 24GB of memory, using 2-bit quantization for the expert weights.
- What license does Nemotron 3.5 Bolt use?
- The OpenMDW License Agreement, version 1.1, which the model card says allows commercial and non-commercial use.