llm.ing

nvidia-nemotron-nano-9b-v2

Nvidiaopen weightsArtificial Analysis ↗

Compact Nemotron model for efficient reasoning and deployable AI agents

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence7.4independentaaJul 24, 2026
Median output speedspeed116 tok/sindependentaaJul 24, 2026
Median time to first tokenspeed2.66sindependentaaJul 24, 2026

Includes index data from Artificial Analysis.