Skip to content
AI Model Radar

NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB

nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
Open Source · chat · open-weights
Open Alert me on changes
Context
256K
Max output
—
Weights
Open
API $/1M
—
Modalities
text · image
Released
07 Oct 2026
License: other · nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
Download image Share on X Share on LinkedIn
AI summary
● machine-written

NVIDIA Nemotron 3.5 Bolt 74B-A9B: 74B open-weights model with 256K context

NVIDIA Nemotron 3.5 Bolt 74B-A9B is an open-weights model compressed from the larger Nemotron 3.5 Super VL 120B-A12B. It supports text and image inputs with a 256K token context window. The model scores 21 on the Artificial Analysis Intelligence Index, positioning it among leading open-weight models of similar size.

What's new
  • Compressed from Nemotron 3.5 Super VL 120B-A12B using model compression
  • Includes C-RADIO v4-H vision encoder for image and video frame processing
  • Supports 256K tokens of context for extended document processing
  • Open-weights format available on Hugging Face in multiple quantizations (24GB, GGUF, BF16)
Best for
Long-context text and image understanding tasksApplications requiring open-weight model deploymentUse cases where commercial licensing restrictions apply
Sources

Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB