MDL
NVIDIA-Nemotron-3-Nano-4B-BF16
nvidia
Parameters
4B
Downloads
1.8M
on HF
Likes
101
Avg score
—
Weights
Open
Released
Mar 7, 2026
About
NVIDIA-Nemotron-3-Nano-4B-BF16 is a 4B-parameter open-weights model in the NVIDIA family from nvidia.
othertext-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMsNemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer ModelsNVIDIA Nemotron 3: Efficient and Open IntelligenceNemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic ReasoningNemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset