# NVIDIA Nemotron 3.5 model releases

> Live situation record from CLSTR: https://clstr.news/situations/nvidia-nemotron-35-model-releases
> Updated: 2026-10-24T03:26:21.000Z. Sources: 5. Developments: 2.

NVIDIA has expanded its Nemotron 3.5 model lineup with releases targeting different hardware capabilities. The Nemotron 3.5 Super VL, a 120B vision-language Mixture-of-Experts model, is designed for high-memory systems, requiring approximately 128GB of memory for local execution. This model features a Mamba-2/Transformer hybrid architecture and a vision encoder capable of processing text, images, and video.

Following this, NVIDIA released the Nemotron 3.5 Bolt E4B, a smaller model optimized for low-memory environments such as voice assistants and robotic interfaces. Derived from Google’s Gemma 4 E4B-it base, the Bolt E4B utilizes reinforcement learning to improve instruction following and tool calling. It is designed to operate with approximately 4GB of memory usage.

## Timeline

### 2026-10-24: NVIDIA releases Nemotron 3.5 Bolt E4B small language model

NVIDIA released Nemotron 3.5 Bolt E4B, a small language model optimized for local agents, voice assistants, and robotics with a target memory footprint of approximately 4GB.

3 sources. https://clstr.news/cluster/nvidia-releases-nemotron-35-bolt-e4b-small-language-model

### 2026-10-16: Nemotron 3.5 Super VL model can run locally on 128GB memory systems

NVIDIA's Nemotron 3.5 Super VL vision-language model can run locally on hardware with 128GB of memory using community-converted formats, bypassing the need for specialized Blackwell GPUs.

2 sources. https://clstr.news/cluster/nemotron-35-super-vl-model-can-run-locally-on-128gb-memory-systems

---
Cite as: NVIDIA Nemotron 3.5 model releases. CLSTR, https://clstr.news/situations/nvidia-nemotron-35-model-releases