Nemotron 3 Super is a 120B mixture-of-experts model with 12B active parameters in NVIDIA's Nemotron 3 family, sitting between Nano and Ultra in scale. It offers stronger reasoning and agentic capability than Nemotron 3 Nano while remaining more efficient than Nemotron 3 Ultra.
Fascia di costo
0.1x
Contesto
262K
Rilasciato
11 mar 2026
Input
Text
Output
Text
Supporto
RagionamentoChiamata di strumentiOutput strutturati
Prestazioni
Latenza e velocità mediane misurate sulle richieste recenti.
Velocità115 tok/s
Latenza1.84s
Ultime notizie su Nemotron 3 Super
Articoli recenti e post della community, con link alle fonti originali.
Beyond Transcription: Nemotron 3.5 Transcribe | Nemotron LabsNVIDIA Developer3,147- Booz Allen Switches to Nvidia’s NemotronThe Information
NVIDIA's Nemotron Bolt 74B-A9B 2 BitSam Witteveen70,394
Nvidia Just Released NVIDIA Nemotron 3.5 Transcribe! 🤯Julian Goldie SEO1,609
Nvidia Nemotron 3.5 Transcribe: open ASR for 40 languagesHacker News13426
NVIDIA's NEW Nemotron 3.5 Bolt 4B Model Is INSANE... I Tested It 10 Ways On An 8GB LaptopPrompt Engineer 481,962
NVIDIA's New 120B AI Model Is INSANE! 🤯 Nemotron 3.5 Super VLDuo Talks AI4,660