Nemotron 3.5 Transcribe is an open-weight, offline speech and audio model for transcription in 40 languages, with support for recordings up to one hour and a 65,536-token context. Its hybrid mixture-of-experts architecture activates approximately 4.3B parameters, including the audio encoder, and it is released in BF16,…
Nemotron-3.5-Embed-8B-BF16 is a multimodal embedding model from NVIDIA that maps text, images, and page screenshots into a shared 4096-dimensional vector space for visual document retrieval and semantic search. Built on the Nemotron-3-Embed-8B text encoder with a vision encoder, it supports up to 32k tokens and Matryos…
Nemotron-3.5-Embed-1B-BF16 is a compact multimodal embedding model from NVIDIA that maps text, images, and page screenshots into a shared 2048-dimensional vector space for visual document retrieval and semantic search. It pairs the Nemotron-3-Embed-1B text encoder with a vision encoder, supports up to 32k tokens and Ma…
Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 2048-dim vectors that can be truncated, and shares the text embedding space of Nemotro…
Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 4096-dim vectors that can be truncated, and shares the text embedding space of Nemotro…
Nemotron 3.5 Rerank 8B is an 8B-parameter reranking model from NVIDIA that scores the relevance of documents to a query, for reordering the candidates retrieved by an embedding model. It supports long inputs up to 32k tokens and pairs naturally with the Nemotron 3.5 Embed models in multilingual RAG pipelines.
Nemotron 3.5 Rerank 8B is an 8B-parameter reranking model from NVIDIA that scores the relevance of documents to a query, for reordering the candidates retrieved by an embedding model. It supports long inputs up to 32k tokens and pairs naturally with the Nemotron 3.5 Embed models in multilingual RAG pipelines.
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool us…
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool us…
Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcription pipelines.
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 benefit from domain-specific customization.
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 benefit from domain-specific customization.
NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval workflows, retaining more than 95% of the 8B model’s accuracy in a smaller deployment footprint.
Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG pipelines handling charts, tables, infographics, and mixed-media documents. It works as a cross-encoder over a text query paired with a do…
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 text and image input and returning text output: a safe/unsafe classification for the user prompt and the respons…
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 supports text input and output with a context window of up to 1M tokens. It is suited for long-running ag…
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 supports text input and output with a context window of up to 1M tokens. It is suited for long-running ag…
Cosmos3-Super-Text2Image is a post-trained text-to-image variant of the Cosmos3-Super base model. Cosmos3 is a collection of omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands, serving as a foundational building block for Physical AI applications and research.
Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34% average word error rate on the HuggingFa…
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 audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.
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 Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token gene…
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.
Canary Speech-to-Text is a real-time speech-to-text model from NVIDIA for fast, accurate transcription of audio. It has built-in punctuation and capitalization, on by default, and can return partial transcripts while it works.