NVIDIA/Text / LLMRuns on a laptop
NVIDIA releases compact Dory 1.0 4B text model
The new Nemotron Labs model packs a 4-billion-parameter language model trained on NVIDIA's Nemotron datasets.
Company
NVIDIA
36 modelsUS
CategoriesText / LLMVision-LanguageSpeech → TextAny-to-AnyText → SpeechEmbeddingsText → VideoText → ImageImage → VideoImage Editing
Releases
NVIDIA/Vision-LanguageWorkstation GPU
NVIDIA's Nemotron 3.5 Super VL Pairs Vision With MoE Efficiency
The 120B-parameter vision-language model activates just 12B per token and ships in NVIDIA's NVFP4 format for leaner inference.
NVIDIA/Vision-LanguageWorkstation GPU
NVIDIA's Nemotron 3.5 Super VL Pairs Vision With MoE
The new vision-language model carries 120B total parameters but activates just 12B per token, aiming to keep multimodal inference efficient.
NVIDIA/Speech → TextWorkstation GPU
NVIDIA's Nemotron 3.5 Transcribe Brings Promptable ASR
A sparse 30B mixture-of-experts model handles multilingual transcription, translation, and speaker diarization from a single system.
NVIDIA/Vision-LanguageWorkstation GPU
NVIDIA's Nemotron-3.5 Bolt targets 24GB GPUs
A multimodal mixture-of-experts model with 74B total parameters but just 9B active, tuned to fit consumer-class hardware.
NVIDIA/Speech → Text
TII Brings Falcon to Speech With New ASR Model
The team behind the Falcon language models expands into speech-to-text with its first automatic speech recognition release.
NVIDIA/Text / LLM
Falcon-Emirati tunes an LLM for local dialect
TII's Falcon family gets a variant built around Emirati Arabic, aiming at culture and nuance rather than generic Gulf Arabic.
NVIDIA/Text / LLMRuns on a laptop
NVIDIA's Nemotron 3.5 Bolt Targets 4GB Devices
The compact 4-billion-parameter text model is tuned for multilingual work on memory-constrained hardware.
NVIDIA/Vision-LanguageRuns anywhere
NVIDIA's Nemotron 3.5 Parse Targets Document OCR
A new vision-language model from NVIDIA is tuned specifically for reading and structuring documents rather than general chat.
NVIDIA/Speech → TextRuns anywhere
NVIDIA's Nemotron-3 Brings Streaming Speaker Diarization
The new open model applies NVIDIA's Sortformer approach to identify who's speaking, in real time.
NVIDIA/Any-to-Any
NVIDIA's Kumo Takes Aim at Tabular Prediction
A new foundation model targets structured data, where spreadsheets and databases still dominate real-world machine learning.
NVIDIA/Text / LLM
Liquid AI's LFM2.5-DSpark targets faster inference
The new efficient language model claims up to 3.2x faster inference, extending Liquid AI's push toward lean, deployable models.
NVIDIA/Text → Speech
NVIDIA Opens Magpie TTS for Multilingual Voice Agents
The open-weights text-to-speech model targets low-latency, deployable voice agents across multiple languages.
NVIDIA/Text → Speech
NVIDIA opens Magpie TTS for multilingual voice agents
The company releases open weights for a low-latency, multilingual text-to-speech model aimed at real-time conversational systems.
NVIDIA/Text → Speech
NVIDIA Opens Magpie TTS for Multilingual Voice Agents
The open-weights text-to-speech model targets low-latency speech synthesis with full control over deployment.
NVIDIA/Text / LLMRuns on a laptop
NVIDIA's Nemotron 3.5 Lightning trims MoE for speed
A 30-billion-parameter mixture-of-experts model activates just 3 billion parameters per token, using a hybrid Mamba design to keep inference fast.
NVIDIA/Text / LLMConsumer GPU
NVIDIA's Nemotron 3.5 Lightning Blends Mamba and MoE
A 30B mixture-of-experts model with just 3B active parameters aims at fast, agentic coding workloads.
NVIDIA/Text → SpeechRuns on a laptop
NVIDIA's Nemotron VoiceChat 11B Targets Spoken AI
An 11-billion-parameter voice conversation model built atop Nemotron Nano 9B v2 arrives on Hugging Face.
NVIDIA/Any-to-Any
NVIDIA's Audio-Visual Flamingo Fuses Sound and Sight
A fully open multimodal model aims to reason jointly across audio, images, and long-form video.
NVIDIA/EmbeddingsRuns on a laptop
NVIDIA's Nemotron-3-Embed 8B tops RTEB retrieval test
The 8-billion-parameter text embedding model claims the number one overall spot on the RTEB benchmark, with an eye toward agentic retrieval.
NVIDIA/EmbeddingsRuns anywhere
NVIDIA's Nemotron 3 Embed tops the RTEB leaderboard
A compact 1B-parameter text embedding model claims the top overall spot on a retrieval benchmark aimed at reflecting real-world use.
NVIDIA/Any-to-AnyConsumer GPU
NVIDIA's Audex Unifies Audio Understanding and Speech
A new 30B mixture-of-experts model from NVIDIA handles both listening and speaking within a single audio-text architecture.
NVIDIA/Text → VideoRuns on a laptop
NVIDIA's Cosmos 3 Edge Brings World Models Closer
A new edge-optimized variant of NVIDIA's Cosmos world-model line aims to run generative video where the compute lives.
NVIDIA/Text → ImageConsumer GPU
NVIDIA distills Qwen-Image for few-step generation
A DMD2-distilled build of Qwen-Image trades sampling steps for speed while keeping the original model's output profile.
NVIDIA/Text / LLMRuns anywhere
Liquid AI's LFM2.5-230M targets phones and robots
A 230-million-parameter language model built to run on hardware as modest as a Raspberry Pi.
NVIDIA/Vision-LanguageRuns anywhere
NVIDIA's Nemotron-Parse 2.0 targets document OCR
A compact vision-language model built to turn scanned pages and complex layouts into structured, machine-readable text.
NVIDIA/Text / LLMWorkstation GPU
NVIDIA's Nemotron 3 Puzzle Runs Big on a Lean Budget
A 75-billion-parameter mixture-of-experts reasoning model that activates just 9 billion parameters per token.
NVIDIA/Text / LLMWorkstation GPU
NVIDIA's Nemotron-3 Puzzle Brings a Lean MoE to Reasoning
The 75B-parameter model activates just 9B per token and ships in NVIDIA's NVFP4 format for efficient inference.
NVIDIA/Image → VideoWorkstation GPU
NVIDIA Releases Cosmos3 Image-to-Video World Model
The latest release in NVIDIA's 'world model' research family aims to generate coherent and realistic video from a single static image.
NVIDIA/Image → Video
NVIDIA Releases SANA, a Camera-Controllable Video Model
The new model, SANA-WM, uses a bidirectional diffusion process to give creators fine-grained control over camera movement and video editing.
NVIDIA/Speech → TextRuns anywhere
NVIDIA Releases Nemotron-3.5 Streaming ASR Model
The 600-million-parameter model uses a FastConformer architecture for real-time, multilingual speech-to-text applications.
NVIDIA/Image Editing
NVIDIA Releases PiD for High-Quality Image Upscaling
The new component is a specialized VAE decoder that works with Stability AI's Z-Image model to enhance super-resolution tasks.
NVIDIA/Any-to-AnyRuns on a laptop
NVIDIA Releases Efficient Nemotron-3 Multimodal MoE
The new 30-billion parameter Mixture-of-Experts model handles text and images while using only 3 billion active parameters for inference.
NVIDIA/Any-to-AnyConsumer GPU
NVIDIA Releases Nemotron-3-Nano Omni-Modal MoE
The new 30-billion-parameter Mixture-of-Experts model handles any combination of modalities with just 3 billion active parameters.
NVIDIA/Text / LLMConsumer GPU
NVIDIA's Nemotron TwoTower is a MoE experiment
An experimental 30B mixture-of-experts base model blends diffusion and Mamba ideas under a two-tower design.
NVIDIA/Text / LLMConsumer GPU
NVIDIA's Nemotron TwoTower mixes diffusion and Mamba
A new 30B mixture-of-experts base model activates just 3B parameters per token and pairs a hybrid diffusion/Mamba design.
NVIDIA/Vision-LanguageRuns anywhere
NVIDIA's New 3B VLM Pinpoints Objects in Images
The new 3-billion-parameter model, based on the company's Eagle architecture, is designed for high-precision visual grounding tasks.
NVIDIA/Speech → TextRuns anywhere
NVIDIA Releases Streaming Speech-to-Text Model
The 600-million-parameter Nemotron model is designed for real-time English transcription using a cache-aware FastConformer architecture.
NVIDIA/Speech → Text
NVIDIA Releases Real-Time Speaker Diarization Model
The new Sortformer-based model is designed for streaming audio, identifying up to four distinct speakers in real time.
NVIDIA/Speech → TextRuns anywhere
NVIDIA's Parakeet ASR Tackles Multi-Speaker Audio
The 600-million-parameter model offers real-time speech-to-text with speaker diarization, built on the efficient FastConformer architecture.
NVIDIA/Speech → TextRuns anywhere
NVIDIA Releases Canary 1B v2 Multilingual Speech Model
The new 1-billion-parameter model handles both transcription and translation across five languages using the company's efficient FastConformer architecture.
NVIDIA/Speech → TextRuns anywhere
NVIDIA Releases 600M Parakeet for Speech Recognition
The new FastConformer model uses a specialized training technique to improve transcription accuracy in noisy, real-world environments.
NVIDIA/Speech → TextRuns anywhere
NVIDIA Fuses LLM and ASR in Canary-Qwen 2.5B Model
The 2.5 billion-parameter speech model combines a FastConformer encoder with a Qwen LLM decoder, a hybrid approach to transcription.
