NVIDIA

Nemotron Labs 3 Competitive Coding

NVIDIA

Nemotron Labs 3 Competitive Coding is an open-weight NVIDIA language-model release. A competitive-programming specialist trained from the Nemotron 3 Ultra base model with supervised learning and reasoning reinforcement learning. It generates candidate algorithmic solutions and supports research on difficult coding contests. The public checkpoint is NVFP4. Contest results involving multiple candidate searches or GenCorrect evaluate a system rather than a single response. The license permits commercial and non-commercial use subject to its published terms.

Nemotron Labs Ultra Math

NVIDIA

Nemotron Labs Ultra Math is an open-weight NVIDIA language-model release. NVIDIA’s released olympiad mathematics specialists build on Nemotron 3 Ultra for rigorous proof generation, checking, and self-evaluation. The SFT and reinforcement-learning checkpoints are grouped here. They were used in an ensemble with inference-time scaling for IMO-level problem solving; ensemble medal-level claims are not standalone model accuracy. The license permits commercial and non-commercial use subject to its published terms.

Nemotron Labs Teachers

NVIDIA

Nemotron Labs Teachers is an open-weight NVIDIA language-model release. A released family of domain-specialized Nemotron 3 Ultra teacher checkpoints. Chat, instruction following, general reasoning, STEM, and competitive coding teachers provide differentiated training signals for multi-teacher on-policy distillation. The chat checkpoint is also a standalone reasoning and conversation model, not merely a reward scorer. The license permits commercial and non-commercial use subject to its published terms.

Nemotron 3.5 Lightning

NVIDIA

Nemotron 3.5 Lightning is an open-weight NVIDIA language-model release. A compact active-parameter reasoning model designed for fast specialized steps in long-running agents. It interleaves Mamba-2, attention, and sparse experts, with speculative decoding options. BF16 weights support customization, while optimized NVFP4 variants target production inference. The license permits commercial and non-commercial use subject to its published terms.

Nemotron Labs VoiceChat

NVIDIA

Nemotron Labs VoiceChat is an open-weight full-duplex voice assistant that combines a streaming Conformer speech encoder, Nemotron Nano v2 language model, and speech decoder. It can listen and speak during an ongoing conversation and emit structured function calls through a separate output channel. The released 11B system is intended for spoken-assistant research and customization, including interaction timing and tool use. The weight card dates public distribution to August 3, 2026; earlier service previews do not establish the availability of this exact downloadable checkpoint.

Nemotron Labs 3 Puzzle

NVIDIA

Nemotron Labs 3 Puzzle is an open-weight NVIDIA language-model release. Puzzle is a deployment-oriented structural compression of Nemotron 3 Super. It reduces the teacher’s parameter and expert budget while retaining its hybrid architecture, reasoning behavior, and multi-token prediction. NVIDIA releases BF16, FP8, and NVFP4 checkpoints for different serving systems. The license permits commercial and non-commercial use subject to its published terms.

Nemotron Labs Audex

NVIDIA

Audex is NVIDIA’s unified audio-text language-model family, designed to add speech and sound understanding and generation while retaining text reasoning. Audio encoders project inputs into the language embedding space; quantized audio and text tokens share a decoder. The main 30B sparse checkpoint builds on Nemotron-Cascade 2, and a smaller dense 2B tier is also released. It supports audio question answering, spoken dialogue, speech translation, and text reasoning. The research paper publicly releases the checkpoints on July 6; the card’s June 8 date conflicts with that publication record.

Audio Visual Flamingo

NVIDIA

Audio Visual Flamingo is an open-weight NVIDIA audio-language research model. AVF combines audio and video evidence with textual instructions for synchronized event understanding and natural-language answers. It uses a Qwen2.5-7B backbone, audio front-end, and vision components derived from NVIDIA’s multimodal research. The final released checkpoint is dated June 29, 2026; earlier repository creation is not used as evidence of public availability. The release supports research use under a non-commercial license. Descriptions of perceptual content are generated language and can misidentify events, speakers, or musical attributes.

Nemotron Labs TwoTower

NVIDIA

Nemotron Labs TwoTower is an open research language model that separates autoregressive context processing from block-wise diffusion generation. A frozen Nemotron 3 Nano context tower encodes preceding clean tokens, while a trainable denoiser tower refines blocks through cross-attention. The released system contains both sparse towers. It investigates parallel token generation and the quality-throughput tradeoff rather than a new chat product. Reported speedups depend on block size, confidence thresholds, hardware, and the autoregressive baseline used in the paper.

Nemotron 3 Ultra

NVIDIA

Nemotron 3 Ultra is an open-weight NVIDIA language-model release. The largest released Nemotron 3 tier targets difficult reasoning, software engineering, and long-running tool workflows. Latent mixture-of-experts routing and multi-token prediction support efficient frontier-scale training and serving. Downloadable base and post-trained weights are available in several precisions. The license permits commercial and non-commercial use subject to its published terms.

Cosmos 3 Super Reasoner

NVIDIA

Cosmos 3 Super Reasoner is the language-generating 32B reasoning tower of NVIDIA’s Cosmos 3 Super world model, adapted from the Qwen3-VL 32B architecture. It accepts text, images, and video and produces textual reasoning about physical scenes, spatial relationships, trajectories, and visual events with a documented 256K context. NVIDIA’s downloadable Cosmos3-Super checkpoint packages this autoregressive tower with a separate 32B diffusion generator, making the full omnimodal checkpoint 64B rather than a 64B language reasoner. NIM exposes the reasoning tower as nvidia/cosmos3-super-reasoner; Nano’s 8B reasoner is a smaller family variant. OpenMDW 1.1 permits commercial and non-commercial model use.

Nemotron Labs Diffusion

NVIDIA

Nemotron Labs Diffusion is a tri-mode research family that unifies autoregressive generation, diffusion decoding, and self-speculative decoding in one trained language model. Different attention patterns and decoding procedures let users explore generation speed and output quality with a shared checkpoint. Released 3B, 8B, and 14B language tiers include base and instruction models; a related 8B vision-language checkpoint adds image input. The research targets inference efficiency and hybrid decoding, and measured throughput is specific to the chosen sampler and hardware.

Nemotron Labs 3 Elastic

NVIDIA

Nemotron Labs 3 Elastic is an open-weight NVIDIA language-model release. Star Elastic packages several nested reasoning models in a single checkpoint derived from Nemotron 3 Nano. Importance-based component ranking and elastic post-training let developers extract smaller subnetworks without independently training each size. The 23B and 12B variants share the larger checkpoint’s parameter space. The license permits commercial and non-commercial use subject to its published terms.

Nemotron 3 Nano Omni

NVIDIA

Nemotron 3 Nano Omni combines a Nemotron 3 Nano language backbone with image and audio encoders for unified multimodal reasoning. It accepts text, images, audio, and video and produces textual answers, summaries, and tool calls. The model targets document understanding, video question answering, and spoken-input agents while avoiding a separate model for each input type. The backbone has approximately 31B parameters with about 3B active; encoder parameters and multimodal tokens also contribute to memory and context usage.

Audio Flamingo Next

NVIDIA

Audio Flamingo Next is an open-weight NVIDIA audio-language research model. The successor to Audio Flamingo 3 improves speech, environmental-sound, and music reasoning and handles audio up to thirty minutes. Temporal Audio Chain-of-Thought grounds intermediate reasoning in timestamps. Instruct, thinking, and captioner checkpoints are variants of the same research release. The release supports research use under a non-commercial license. Descriptions of perceptual content are generated language and can misidentify events, speakers, or musical attributes.

Nemotron-Cascade 2

NVIDIA

Nemotron-Cascade 2 is a sparse reasoning model post-trained through cascade reinforcement learning and multi-domain on-policy distillation. The training recipe transfers specialist strengths across mathematical reasoning, coding, science, and instruction following into a compact active-parameter model. It supports thinking and non-thinking modes and very long context. NVIDIA releases weights, training datasets, and reproducibility materials, making the checkpoint useful for reasoning research as well as self-hosted assistants. Competition-level results may rely on extended inference or tool setups.

Nemotron 3 Super

NVIDIA

Nemotron 3 Super is an open-weight NVIDIA language-model release. A long-context reasoning model for software engineering and multi-step agents. It uses latent-space routed experts, selective attention, multi-token prediction, and an NVFP4 training recipe. The public research release is dated March 10; the weight card records March 11 distribution. The license permits commercial and non-commercial use subject to its published terms.

Nemotron 3 Nano

NVIDIA

Nemotron 3 Nano is a 31.6B parameter hybrid large language model developed by NVIDIA, released on December 15, 2025. It employs a novel Hybrid Mamba-Transformer Mixture-of-Experts (MoE) architecture, activating only ~3.2B parameters per token for efficient inference. Optimized for agentic AI, reasoning, and coding, it supports a 1 million token context window and features a 'Reasoning ON/OFF' toggle with a configurable thinking budget. NVIDIA has released the model with open weights, training data, and training recipes under the NVIDIA Open Model License.

Nemotron-Cascade

NVIDIA

Nemotron-Cascade is NVIDIA’s family of small dense reasoning models trained with sequential reinforcement learning across multiple task domains. The release explores how staged training can improve mathematics, coding, alignment, and agent tasks without losing earlier skills. The 8B and 14B checkpoints include dedicated thinking and standard-response variants. Long-context evaluations apply model-specific RoPE scaling, so their 64K or 90K evaluation windows should not be treated as uniform native context limits. Weights and evaluation scripts support research and adaptation.

Music Flamingo

NVIDIA

Music Flamingo is an open-weight NVIDIA audio-language research model. This specialist extends Audio Flamingo 3 for music descriptions, question answering, temporal structure, harmony, instrumentation, and lyric understanding. Rotary time embeddings preserve alignment across long tracks, and supervised reasoning followed by reinforcement learning improves theory-focused responses. January 2026 and thinking checkpoints remain variants. The release supports research use under a non-commercial license. Descriptions of perceptual content are generated language and can misidentify events, speakers, or musical attributes.

Nemotron Nano 2 VL

NVIDIA

Nemotron Nano 2 VL is an NVIDIA language-model family. A vision-language specialization for document intelligence, multi-image reasoning, and video understanding. It handles invoices, receipts, manuals, charts, and visual questions, emitting natural-language answers. BF16 and quantized variants share the same model identity. Downloadable weights enable experiments and adaptation, subject to the checkpoint-specific license. Model-generated text and reasoning can be inaccurate, so capability claims should be checked in the intended application.

Nemotron Nano 2

NVIDIA

Nemotron Nano 2 is an NVIDIA language-model family. A small hybrid reasoning model designed for efficient deployment and agent tool use. It supports configurable reasoning and multilingual instruction following. Most layers use state-space sequence modeling, with attention retained for selected tasks; its deployment tradeoffs differ from a purely attention-based model. Downloadable weights enable experiments and adaptation, subject to the checkpoint-specific license. Model-generated text and reasoning can be inaccurate, so capability claims should be checked in the intended application.

Audio Flamingo 3

NVIDIA

Audio Flamingo 3 is an open-weight NVIDIA audio-language research model. It uses a unified AF-Whisper encoder, an adaptor, and Qwen2.5-7B language backbone to answer questions about speech, sounds, and music. Audio inputs can span ten minutes. A chat variant adds multi-turn audio conversation and streaming speech output. The release supports research use under a non-commercial license. Descriptions of perceptual content are generated language and can misidentify events, speakers, or musical attributes.

Nemotron-H

NVIDIA

Nemotron-H is an NVIDIA language-model family. First published in April 2025, this research family studies efficient hybrid language models built primarily from Mamba-2 and MLP layers with selected attention layers. The initial release supplies completion checkpoints; later reasoning and long-context variants have their own cards and license terms. The representative initial 8B base supports 8K context. Downloadable weights enable experiments and adaptation, subject to the checkpoint-specific license. Model-generated text and reasoning can be inaccurate, so capability claims should be checked in the intended application.

Llama Nemotron

NVIDIA

Llama Nemotron is an NVIDIA language-model family. NVIDIA’s Llama-derived reasoning family post-trains and compresses Meta checkpoints for enterprise agents. Nano and Super were released in March; the 253B Ultra followed in April. Reasoning can be switched on for difficult tasks or off for concise responses. Super derives from Llama 3.3 70B; ancestry differs across tiers. Downloadable weights enable experiments and adaptation, subject to the checkpoint-specific license. Model-generated text and reasoning can be inaccurate, so capability claims should be checked in the intended application.

Nemotron-4

NVIDIA

Nemotron-4 is an NVIDIA language-model family. The 340B family supplies base and instruction models for synthetic data generation and downstream customization. A companion reward model is a pipeline component rather than a separate generative language-model page. The instruction checkpoint is optimized for English single- and multi-turn conversation. Downloadable weights enable experiments and adaptation, subject to the checkpoint-specific license. Model-generated text and reasoning can be inaccurate, so capability claims should be checked in the intended application.