LLM EXPLORER 64,924 MODELS INDEXED

NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB by nvidia

By nvidia · 6060 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB is an open-source language model by nvidia. Features: 74b LLM, VRAM: 8.8GB, License: other, LLM Explorer Score: 0.45.

  Arxiv:2502.02631   Arxiv:2502.05003   Arxiv:2601.20088   Arxiv:2605.07182   8-bit Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Conversational   Custom code Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr...   De   En   Endpoints compatible   Es   Fr   Image-text-to-text   It   Ja   Modelopt   Nemotron-3.5   Nemotron h omni   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB 

NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB Parameters and Internals

LLM NameNVIDIA Nemotron 3.5 Bolt 74B A9B 24GB
Repository 🤗https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB 
Base Model(s)  nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16   nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
Model Size74b
Required VRAM8.8 GB
Updated2026-10-19
Maintainernvidia
Model Typenemotron_h_omni
Model Files  1.6 GB: 1-of-90   0.1 GB: 2-of-90   0.3 GB: 3-of-90   0.1 GB: 4-of-90   0.2 GB: 5-of-90   0.1 GB: 6-of-90   0.3 GB: 7-of-90   0.1 GB: 8-of-90   0.0 GB: 9-of-90   0.4 GB: 10-of-90   0.1 GB: 11-of-90   0.3 GB: 12-of-90   0.1 GB: 13-of-90   0.3 GB: 14-of-90   0.1 GB: 15-of-90   0.3 GB: 16-of-90   0.1 GB: 17-of-90   0.0 GB: 18-of-90   0.4 GB: 19-of-90   0.1 GB: 20-of-90   0.4 GB: 21-of-90   0.1 GB: 22-of-90   0.6 GB: 23-of-90   0.1 GB: 24-of-90   0.5 GB: 25-of-90   0.1 GB: 26-of-90   0.0 GB: 27-of-90   0.3 GB: 28-of-90   0.1 GB: 29-of-90   0.5 GB: 30-of-90   0.1 GB: 31-of-90   0.4 GB: 32-of-90   0.1 GB: 33-of-90   0.4 GB: 34-of-90   0.1 GB: 35-of-90
Supported Languagesen es fr de it ja
Model ArchitectureNemotronH_Omni_Reasoning_V3
Licenseother
Transformers Version5.8.1