Skip to content
AI Model Radar

NVIDIA Nemotron 3.5 Bolt E4B 4GB

nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
Open Source · chat · open-weights
Open Alert me on changes
Context
—
Max output
—
Weights
Open
API $/1M
—
Modalities
text
Released
05 Oct 2026
License: other · nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
Download image Share on X Share on LinkedIn
AI summary
● machine-written

NVIDIA Nemotron 3.5 Bolt E4B 4GB: Open-weights text model announced October 2026

NVIDIA announced Nemotron 3.5 Bolt E4B, a smaller open-weights model targeting a 4GB footprint for local deployment. The model was announced October 15, 2026, with a planned release date of October 23, 2026, though verified availability and exact specifications remain unconfirmed. Pricing is unverified and the model is offered at no per-token cost according to initial reports.

What's new
  • Announced for 4GB local device footprint, distinct from larger Bolt variants
  • Announced October 15, 2026; planned release October 23, 2026
  • Open-weights model with unverified API and download availability
  • No per-token pricing reported, though not yet independently verified
Best for
Local deployment on resource-constrained devicesText-only tasks requiring compact model footprint
Sources

Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB