NVIDIA

About NVIDIA

NVIDIA pioneered accelerated computing to tackle challenges no one else can solve. Our work in AI and digital twins is transforming the world's largest industries and profoundly impacting society.

Accelerated computing and AI have fully arrived. The acceleration of deep learning ignited the Big Bang of AI. Now, generative AI is a new computing platform, like the PC, internet, and mobile-cloud.

Credit: Runway AI, Adobe, Tabnine, WPP

Website ↗

Source ↗ · 2026-11-12T02:17:03.556571681Z

366 indexed models

366 matching models

nvidia/Nemotron-3.5-Rerank-8B-BF16

azureFoundry/azure-huggingface/nvidia--nemotron-3.5-rerank-8b-bf16@1

Multilingual query/document relevance scoring with an 8B multimodal reranker.

Context window
32,768
Input modalities
text
Output modalities
text

Benchmarks

  • MTEB: 60.301%

Inference prices

  • Published price : $0.05 / input_tokens_per_million · deepInfra ↗

NVIDIA: Nemotron 3.5 Rerank 8B (free)

nvidia/nemotron-3.5-rerank-8b-20261021

Context window
32,768
Input modalities
text, image
Output modalities
rerank
Capabilities
multimodal, rerank, visionInput

NVIDIA Nemotron 3.5 Super VL

vercelAIGatewayCatalog/nvidia/nemotron-3.5-super-vl

NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and document understanding. Its hybrid Mamba-2, attention, and Mixture-of-Experts architecture has 120B total parameters with 12B active per token. Baseten serves text and image inputs with u

Context window
1,048,576
Maximum output
1,048,576
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

NVIDIA: Nemotron 3.5 Transcribe

nvidia/nemotron-3.5-transcribe-20261028

Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters. It transcribes recordings of up to one hour in 40 languages, with speaker attribution, speech translation, and prompt-guided vocabulary and st

Context window
0
Input modalities
audio
Output modalities
transcription
Capabilities
audioInput

Benchmarks

  • Open ASR Leaderboard: 5.27%

NVIDIA Nemotron 3 Content Safety NIM microservice · azureml-nvidia v1

azureFoundry/azureml-nvidia/NVIDIA-Nemotron-3-Content-Safety-NIM-microservice@1

Nemotron-3-Content-Safety is a multimodal, multilingual 4B-parameter content-safety model fine-tuned from Google's Gemma-3-4B-it. It acts as a content-safety moderator for both inputs (prompt + optional image) to and responses from LLMs and VLMs, returning

Input modalities
text, image
Output modalities
text
Capabilities
multimodal, visionInput

nvidia/Nemotron-3-Embed-1B-BF16

azureFoundry/azure-huggingface/nvidia--nemotron-3-embed-1b-bf16@1

Multilingual 1B embedding model for retrieval, semantic search, and RAG with flexible 2048-dim vectors.

Context window
32,768
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • MTEB: 50.777%

Inference prices

  • Published price : $0.02 / input_tokens_per_million · deepInfra ↗

NVIDIA: Nemotron 3 Embed 1B (free)

nvidia/nemotron-3-embed-1b-20260716

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

Context window
4,096
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Inference prices

nvidia/Nemotron-3-Embed-1B-NVFP4

azureFoundry/azure-huggingface/nvidia--nemotron-3-embed-1b-nvfp4@1

NVFP4-quantized multilingual 1B embedding model for retrieval, semantic search, and RAG.

Context window
32,768
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Inference prices

  • Published price : $0.01 / input_tokens_per_million · deepInfra ↗

nvidia/Nemotron-3-Embed-8B-BF16

azureFoundry/azure-huggingface/nvidia--nemotron-3-embed-8b-bf16@1

Multilingual 8B embedding model for retrieval, semantic search, and RAG with flexible 4096-dim vectors.

Context window
32,768
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • MTEB: 61.897%

NVIDIA Nemotron 3 Nano NIM microservice · azureml-nvidia v1

azureFoundry/azureml-nvidia/NVIDIA-Nemotron-3-Nano-NIM-microservice@1

**Nemotron 3 Nano** is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. T

Input modalities
text
Output modalities
text

NVIDIA Nemotron 3 Nano NIM microservice · azureml-nvidia v2

azureFoundry/azureml-nvidia/NVIDIA-Nemotron-3-Nano-NIM-microservice@2

**Nemotron 3 Nano** is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. T

Input modalities
text
Output modalities
text

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

azureFoundry/HuggingFace/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-nvfp4@1

`nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or

Input modalities
text
Output modalities
text

NVIDIA Nemotron 3 Super 120B A12B

vercelAIGatewayCatalog/nvidia/nemotron-3-super-120b-a12b

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. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. A

Context window
256,000
Maximum output
32,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

NVIDIA Nemotron 3 Super NIM microservice · azureml-nvidia v1

azureFoundry/azureml-nvidia/NVIDIA-Nemotron-3-Super-NIM-microservice@1

**Nemotron-3-Super-120B-A12B** is a large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for collaborative agents and high-volume workloads such as IT ticket automation. Like other models in

Input modalities
text
Output modalities
text

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace