NVIDIA·released 2025-12-041 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by NVIDIA and released in 2025, this model is a large-scale system with 31.58 billion parameters, a size that buys more capability headroom while raising compute and serving costs.
3 cited facts
This model is not yet benchmarked, with zero tracked benchmarks on record. Consequently, it holds no current top score.
2 cited facts
The average SOTA gap is unknown, so the comparison cannot be quantified from the available data. It holds the top score on 0 benchmarks, which means no genuine category leadership yet.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is an AI model developed by NVIDIA, released 2025-12-04. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.