Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning)
by NVIDIA
Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) is a reasoning model from NVIDIA, released on October 15, 2026. It ranks #106 of 247 models by Intelligence Score with a score of 29.
NVIDIA Nemotron 3.5 Bolt is an open multimodal 74B total / 9B active Mixture-of-Experts vision-language model for local / edge agentic workloads. Compressed from Nemotron 3.5 Super VL into a native IQ2 (2-bit) 24GB footprint for RTX / DGX Spark and similar systems, with a hybrid Mamba-2 + LatentMoE + Attention backbone and C-RADIO v4-H vision encoder. Accepts text, image, and video inputs and produces text; up to 256K context; tool use and configurable reasoning. A full-precision BF16 sibling is published at nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16. Released under OpenMDW-1.1.
Key specs
| Provider | NVIDIA |
|---|---|
| Release date | 2026-10-15 |
| License | open weights |
| Intelligence Score | 29 |
| Coding index | 15 |
Quick answers
Is Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) open source?
Yes. Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) is an open model released under the open weights license.
When was Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) released?
NVIDIA released Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) on October 15, 2026.
How does Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) compare to Claude Opus 5.5 (Reasoning)?
Nemotron 3.5 Bolt (74B A9B 24GB) (Reasoning) scores 29 on the Intelligence Score versus 59.9 for Claude Opus 5.5 (Reasoning), the current #1.
Compare on the AI leaderboard · All AI models