Skip to content
AI Model Radar

NVIDIA Nemotron Labs Dory1.0 4B BF16

nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16
Open Source · chat · open-weights
Open Alert me on changes
Context
262.1K
Max output
—
Weights
Open
API $/1M
—
Modalities
text
Released
16 Oct 2026
License: other · nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16
Download image Share on X Share on LinkedIn
AI summary
● machine-written

NVIDIA Nemotron Labs Dory1.0 4B BF16 open-weights chat model

A 4 billion parameter text-based chat model from NVIDIA released as open weights. Pre-trained on 6 trillion tokens with support for 256K context length, following a context-extension phase of 300 billion tokens. Available in multiple quantization formats including BF16, NVFP4, GGUF, and MXFP8.

What's new
  • Supports up to 256K context length
  • Pre-trained with 6 trillion tokens using mixed precision (NVFP4 for ~4.5T tokens, BF16 for remainder)
  • Underwent 300 billion token context-extension phase
  • Available in multiple quantization formats for different deployment scenarios
Best for
Text-based conversational tasksDeployment on resource-constrained environmentsLong-context document processing
Sources

Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16