Hugging Face's logo
nvidia 's Collections
NVIDIA Cosmos
NVIDIA Nemotron v3
NVIDIA OmniDreams
Nemotron-Labs-Diffusion
Inference Optimized Checkpoints (with Model Optimizer)
Nemotron-Labs-Elastic
swe-zero-to-swe-hero
Cosmos1
Efficient-DLM
AnyFlow
Nemotron Supervised Fine-Tuning
Nemotron Vision-Language
Nemotron Agentic & Tool-Use
Nemotron Safety & Content Moderation
Nemotron Chat & Instruction Following
Nemotron Code & SWE
Nemotron Math & Reasoning
Nemotron Reward Modeling
Lyra
NVIDIA Ising
NVIDIA EGM
PixelDiT
Nemotron-Cascade 2
NvPanoptix-3D
Kimodo-v1
BioNeMo - Design
GR00T-N1.7
GR00T-N1.6
MedTech Open Models
Cosmos3
Nemotron-Terminal
Nemotron Speech
Speculative Decoding Modules
Nemotron OCR and Object Detection
Nemotron ColEmbed V2
Steering Reasoning VLAs
Earth-2
Cosmos2
Nemotron-Cascade
Nemotron-Post-Training-v3
Nemotron-Pre-Training-Datasets
Nemotron RAG
NeMo Gym
Cosmos Policy
KVzap
NVIDIA Nemotron V2
Alpamayo
ChronoEdit
PhysicsNeMo
Cosmos-Drive-Dreams
Reward Models 10-2025
Llama Nemotron
Clara Medical
BioNeMo - Understand
BioNeMo - Optimize
Cosmos-Predict2.5
Cosmos-Reason2
Nemotron-Personas
Llama-Embed-Nemotron-8B
GEN3C
Reasoning Efficiency Research
BioNeMo
ViPE
OpenReasoning-Nemotron
Cosmos-Predict2
Audio2Face-3D
Reward Models 06-2025
Cosmos-Transfer2.5
AceReason
Nemotron-H
Cosmos-Embed1
Describe Anything
AceMath-RL
OpenMathReasoning
OpenCodeReasoning
OpenCodeReasoning-II
Llama Nemotron Feedback-Edit Inference-Time Scaling
Scoring Verifiers
Nemotron-UltraLong
Cosmos-Reason1
Cosmos-Transfer1
Cosmos-Predict1
Cosmos-Tokenizer1
Llama-3.1-Nemotron-70B
Physical AI
NVILA-Speech-Audio-Setups
QLIP
Cosmos-Preidct1
DMC
AceMath
NemoGuard
Eagle
NeMo Audio Codecs
Hymba
Optimized ONNX models for NVIDIA RTX GPUs
Riva
NVLM 1.0
OpenMath-2
Nemotron 4 340B
SteerLM
Parakeet ASR
Canary ASR/AST
InstructRetro
OpenMath
RLHF
NV-Embed
Llama3-ChatQA-1.5
SSMs
Nemotron 3 8B
BigVGAN
MambaVision
PS3: Scaling Vision Pre-Training to 4K Resolution
Minitron
RADIO
Llama3-ChatQA-2
NeMo Curator - Classifier Models
Nemotron v3 Pre-Training

Cosmos3

Omnimodal World Models for Physical AI

Upvote
117