llm.ing

nemotron-3-nano-30b-a3b

Nvidiaopen weightsOpenRouter ↗Hugging Face ↗Artificial Analysis ↗

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Agentic Indexagentic2.0mirroropenrouterJul 23, 2026
AA Coding Indexcoding14.4mirroropenrouterJul 23, 2026
AA Intelligence Indexintelligence14.2mirroropenrouterJul 23, 2026
7.4independentaaJul 24, 2026
Median output speedspeed103 tok/sindependentaaJul 24, 2026
Median time to first tokenspeed0.71sindependentaaJul 24, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Crusoefp8262K$0.05 · $0.260.91%
DeepInfrafp4262K$0.05 · $0.296.90%
Nebiusfp8262K$0.06 · $0.2492.40%
Novitafp4262K$0.05 · $0.276.61%