Deploying Open Source Vision Language Models (VLM) on Jetson
•
33
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Mode Seeking meets Mean Seeking for Fast Long Video Generation
VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
Articles
Open, Production-ready Enterprise Models
-
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16
Text Generation • 32B • Updated • 60.2k • 110 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Text Generation • 32B • Updated • 977k • 659 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Text Generation • 32B • Updated • 1.41M • • 295 -
nvidia/Qwen3-Nemotron-235B-A22B-GenRM
Text Generation • Updated • 320 • 28
Open, state-of-the-art, production‑ready enterprise speech models from the NVIDIA Speech research team for ASR, TTS, Speaker Diarization and S2S
-
Nemotron Speech Streaming
🎤55Real-time speech recognition with NVIDIA Triton
-
nvidia/nemotron-speech-streaming-en-0.6b
Automatic Speech Recognition • Updated • 14.7k • 484 -
Magpietts Demo
🐠10Generate multilingual speech from text with selectable voices
-
nvidia/magpie_tts_multilingual_357m
Text-to-Speech • Updated • 1.32k • 104
State-of-the-Art Late Interaction Vision-Language Embedding Models
Collection of datasets used in the post-training phase of Nemotron Nano and Super v3.
Set of tools to build retrieval-augmented generation (RAG) systems, improve search and ranking accuracy, and extract structured data from complex docs
Open, Production-ready Enterprise Models
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation • 50B • Updated • 87k • 227 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 18.8k • 24 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
Text Generation • Updated • 660 • • 343 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1
Text Generation • 50B • Updated • 25.4k • 320
State-of-the-Art Text Embedding Model
Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge
-
nvidia/Llama-3_3-Nemotron-Super-49B-GenRM
Text Generation • 50B • Updated • 501 • 18 -
nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual
Text Generation • 50B • Updated • 51 • 6 -
nvidia/Llama-3.3-Nemotron-70B-Reward
Text Generation • 71B • Updated • 119 • 2 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 15 • 10
Novel ITS approach for open-ended tasks - No. 1 on Arena Hard on 18 Mar 2025
SOTA models on Arena Hard and RewardBench as of 1 Oct 2024.
-
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Text Generation • Updated • 6k • 2.06k -
nvidia/Llama-3.1-Nemotron-70B-Reward-HF
71B • Updated • 1.42k • 90 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 14.2k • 440 -
HelpSteer2-Preference: Complementing Ratings with Preferences
Paper • 2410.01257 • Published • 24
The Nemotron 3 8B Family of models is optimized for building production-ready generative AI applications for the enterprise.
We are releasing Nemotron-Terminal models and training datasets.
Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Large scale pre-training datasets used in the Nemotron family of models.
Open, Production-ready Enterprise Models. Nvidia Open Model license.
-
nvidia/NVIDIA-Nemotron-Nano-12B-v2
Text Generation • Updated • 20k • • 155 -
nvidia/NVIDIA-Nemotron-Nano-9B-v2
Text Generation • 9B • Updated • 269k • 483 -
nvidia/NVIDIA-Nemotron-Nano-9B-v2-Base
Text Generation • 9B • Updated • 175k • 43 -
nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base
Text Generation • Updated • 1.65k • 88
A collection of multilingual, region-specific synthetic persona datasets that support sovereign AI development across many countries and regions.
Collection of models for OpenReasoning-Nemotron which are trained on 5M reasoning traces for Math, Code and Science.
-
nvidia/OpenReasoning-Nemotron-1.5B
Text Generation • 2B • Updated • 793 • 54 -
nvidia/OpenReasoning-Nemotron-7B
Text Generation • Updated • 1.21k • • 49 -
nvidia/OpenReasoning-Nemotron-14B
Text Generation • Updated • 826 • 43 -
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 671 • • 121
Mamba-Transformer hybrid models
-
nvidia/Nemotron-H-47B-Reasoning-128K
Text Generation • 47B • Updated • 132 • 20 -
nvidia/Nemotron-H-8B-Reasoning-128K
Text Generation • 8B • Updated • 197 • 25 -
nvidia/Nemotron-H-8B-Reasoning-128K-FP8
Text Generation • 8B • Updated • 26 • 12 -
nvidia/Nemotron-H-47B-Reasoning-128K-FP8
Text Generation • Updated • 513 • 5
Nemotron-4: open models for Synthetic Data Generation (SDG). Includes Base, Instruct, and Reward models.
Large scale pre-training datasets used in the Nemotron family of models.
Open, Production-ready Enterprise Models
-
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16
Text Generation • 32B • Updated • 60.2k • 110 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Text Generation • 32B • Updated • 977k • 659 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Text Generation • 32B • Updated • 1.41M • • 295 -
nvidia/Qwen3-Nemotron-235B-A22B-GenRM
Text Generation • Updated • 320 • 28
We are releasing Nemotron-Terminal models and training datasets.
Open, state-of-the-art, production‑ready enterprise speech models from the NVIDIA Speech research team for ASR, TTS, Speaker Diarization and S2S
-
Nemotron Speech Streaming
🎤55Real-time speech recognition with NVIDIA Triton
-
nvidia/nemotron-speech-streaming-en-0.6b
Automatic Speech Recognition • Updated • 14.7k • 484 -
Magpietts Demo
🐠10Generate multilingual speech from text with selectable voices
-
nvidia/magpie_tts_multilingual_357m
Text-to-Speech • Updated • 1.32k • 104
State-of-the-Art Late Interaction Vision-Language Embedding Models
Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Collection of datasets used in the post-training phase of Nemotron Nano and Super v3.
Large scale pre-training datasets used in the Nemotron family of models.
Set of tools to build retrieval-augmented generation (RAG) systems, improve search and ranking accuracy, and extract structured data from complex docs
Open, Production-ready Enterprise Models. Nvidia Open Model license.
-
nvidia/NVIDIA-Nemotron-Nano-12B-v2
Text Generation • Updated • 20k • • 155 -
nvidia/NVIDIA-Nemotron-Nano-9B-v2
Text Generation • 9B • Updated • 269k • 483 -
nvidia/NVIDIA-Nemotron-Nano-9B-v2-Base
Text Generation • 9B • Updated • 175k • 43 -
nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base
Text Generation • Updated • 1.65k • 88
Open, Production-ready Enterprise Models
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation • 50B • Updated • 87k • 227 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 18.8k • 24 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
Text Generation • Updated • 660 • • 343 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1
Text Generation • 50B • Updated • 25.4k • 320
A collection of multilingual, region-specific synthetic persona datasets that support sovereign AI development across many countries and regions.
State-of-the-Art Text Embedding Model
Collection of models for OpenReasoning-Nemotron which are trained on 5M reasoning traces for Math, Code and Science.
-
nvidia/OpenReasoning-Nemotron-1.5B
Text Generation • 2B • Updated • 793 • 54 -
nvidia/OpenReasoning-Nemotron-7B
Text Generation • Updated • 1.21k • • 49 -
nvidia/OpenReasoning-Nemotron-14B
Text Generation • Updated • 826 • 43 -
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 671 • • 121
Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge
-
nvidia/Llama-3_3-Nemotron-Super-49B-GenRM
Text Generation • 50B • Updated • 501 • 18 -
nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual
Text Generation • 50B • Updated • 51 • 6 -
nvidia/Llama-3.3-Nemotron-70B-Reward
Text Generation • 71B • Updated • 119 • 2 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 15 • 10
Mamba-Transformer hybrid models
-
nvidia/Nemotron-H-47B-Reasoning-128K
Text Generation • 47B • Updated • 132 • 20 -
nvidia/Nemotron-H-8B-Reasoning-128K
Text Generation • 8B • Updated • 197 • 25 -
nvidia/Nemotron-H-8B-Reasoning-128K-FP8
Text Generation • 8B • Updated • 26 • 12 -
nvidia/Nemotron-H-47B-Reasoning-128K-FP8
Text Generation • Updated • 513 • 5
Novel ITS approach for open-ended tasks - No. 1 on Arena Hard on 18 Mar 2025
SOTA models on Arena Hard and RewardBench as of 1 Oct 2024.
-
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Text Generation • Updated • 6k • 2.06k -
nvidia/Llama-3.1-Nemotron-70B-Reward-HF
71B • Updated • 1.42k • 90 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 14.2k • 440 -
HelpSteer2-Preference: Complementing Ratings with Preferences
Paper • 2410.01257 • Published • 24
Nemotron-4: open models for Synthetic Data Generation (SDG). Includes Base, Instruct, and Reward models.
The Nemotron 3 8B Family of models is optimized for building production-ready generative AI applications for the enterprise.
Large scale pre-training datasets used in the Nemotron family of models.