Models

10 modelos

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

por nvidia11 de ago. de 2026262,14 mil de contexto₩ 140 / ₩ 351 · 1M

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

por nvidia11 de ago. de 20261 mi de contextoGrátis / Grátis · 1M

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

por nvidia4 de jun. de 2026131,07 mil de contexto₩ 351 / ₩ 351 · 1M

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

por nvidia4 de jun. de 2026128 mil de contextoGrátis / Grátis · 1M
4,1 tri tokens por semana

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

por nvidia4 de jun. de 2026262,14 mil de contexto₩ 1.097 / ₩ 5.484 · 1M

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

por nvidia4 de jun. de 20261 mi de contextoGrátis / Grátis · 1M

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

por nvidia29 de abr. de 2026256 mil de contextoGrátis / Grátis · 1M

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

por nvidia12 de mar. de 20261 mi de contexto₩ 149 / ₩ 702 · 1M

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

por nvidia12 de mar. de 2026262,14 mil de contextoGrátis / Grátis · 1M

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

por nvidia15 de dez. de 2025262,14 mil de contexto₩ 88 / ₩ 351 · 1M