DigestAI news desk

Cut through the AI noise.

Model · multimodal model

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB is a multimodal model from NVIDIA, first covered on 15 October 2026. It is available as open weights you can download and run (licence: OpenMDW License Agreement, version 1.1). Its context window is 256K tokens.

Last updated

Quick facts

Who makes NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB?
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB is made by NVIDIA. NVIDIA news →
When was NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB released?
The first report of NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB's release that Digest AI covered was published on 15 October 2026.
What type of model is NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB?
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB is a multimodal model.
Are NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB's weights open?
Yes. NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB is released as open weights that can be downloaded and run, under the OpenMDW License Agreement, version 1.1.
What is NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB's context window?
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB's context window is 256K tokens.
Where is NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB available?
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB is available as open weights that can be downloaded and run. huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B ↗

Taken from the coverage, not from our own testing. A question is left out when none of the reports we read gave the answer. All tracked models →

1 story about NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB

  1. NVIDIA releases Nemotron 3.5 Super VL and Bolt edge models with open weights

    NVIDIA launched Nemotron 3.5 Super VL on October 15, 2026, a 120-billion-parameter multimodal model designed for always-on agents. It combines text, image, document, and video understanding with reasoning, instruction…

    6 sources primary source
    maccus.frventurebeat.comThe DecoderUnite.AI +2 more
Other models from NVIDIA