Skip to content
AI Model Radar

NVIDIA Nemotron 3.5 Bolt E4B BF16

nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Open Source · chat · open-weights
Open Alert me on changes
Context
64K
Max output
—
Weights
Open
API $/1M
—
Modalities
text
Released
05 Oct 2026
License: other · nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Download image Share on X Share on LinkedIn
AI summary
● machine-written

NVIDIA Nemotron 3.5 Bolt E4B BF16: 8B text model with 64K context

NVIDIA Nemotron 3.5 Bolt E4B BF16 is an open-weights text model with 8 billion total parameters and 4 billion active parameters, designed for edge deployment and voice assistants. It supports a 64K token context window and ships under the OpenMDW-1.1 license for commercial use.

What's new
  • 8B-parameter model (4B effective) post-trained from Gemma 4 E4B
  • 64K input context window
  • Ships as vLLM checkpoint with BF16 precision variant
  • Targets voice assistants, personas and edge devices
Best for
Edge device deploymentVoice assistant applicationsSingle GPU inferenceTool-calling on constrained hardware
Sources

Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16