**NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF** is a looped (latent-recurrent) large language model (LLM) trained by NVIDIA. The model employs a normalized-GPT architecture with interleaved hybrid sliding window attention (SWA) and full attention layers. By repeatedly applying a shared block of layers, Dory1.0-4B can spend more compute per token allowing it to scale intelligence. This model is ready for commercial or non-commercial use. Dory (Looped LM) Architecture: The layer stack is divided into three groups: Input (I), Recurrent (R) and Output (O). The shared Recurrent block (R) is applied multiple times between the Input and Output blocks, and the input is reinjected into every loop. In Dory, the Input and Output blocks have 8 layers each, while the Recurrent block has 20 layers. Accuracy numbers measured by NVIDIA under a consistent harness (NeMo Gym / Nemo Evaluator SDK). Terminal-Bench 2.1 uses the Terminus-2 harness for all models. † Reported scores.
NVIDIA-Nemotron-Nano-12B-v2 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. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model was fine-tuned from NVIDIA-Nemotron-Nano-12B-v2-Base was further compressed into NVIDIA-Nemotron-Nano-9B-v2. The model uses a hybrid architecture consisting primarily of Mamba-2 and MLP layers combined with just six Attention layers. For the architecture, please refer to the Nemotron-H tech report. The model was trained using Megatron-LM and NeMo-RL. The supported languages include: English, German, Spanish, French, Italian, and Japanese. Improved using Qwen.
NVIDIA-Nemotron-Nano-12B-v2-Base is a large language model (LLM) developed by NVIDIA that is designed as a completion model for a given piece of text. It uses a hybrid model architecture that consists primarily of Mamba-2 and MLP layers with just six Attention layers. The model features a context length of 128K. The supported languages include: English, Spanish, French, German, Japanese, Italian, Portuguese, Chinese, Arabic, Danish, Korean, Dutch, Polish, Russian, Swedish, and Thai. Improved using Qwen. We want to hear from you! Share your ideas, vote on what matters, and help shape the future of Nemotron. The model was trained with 20T tokens, with a batch size of 736, and used the Warmup-Stable-Decay (WSD) learning rate schedule with 8B tokens of learning rate warm up, peak learning rate of 4.5e-4 and minimum learning rate of 4.5e-6. There are a total of 62 layers, of which there are 28 of each MLP and Mamba-2, the remaining layers use GQA with 8 groups
NVIDIA Nemotron Nano v2 12B VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities. Nemotron Nano 12B V2 VL is a model for multi-modal document intelligence. It would be used by individuals or businesses that need to process documents such as invoices, receipts, and manuals. The model is capable of handling multiple images of documents, up to four images at a resolution of 1k x 2k each, along with a long text prompt. The expected use is for tasks like summarization and Visual Question Answering (VQA). The model is also expected to have a significant advantage in throughput. **Architecture Type:** Transformer **Network Architecture:** Vision Encoder: CRadioV2-H Language Encoder: NVIDIA-Nemotron-Nano-12B-v2
NVIDIA-Nemotron-Nano-VL-12B-V2-FP8 is the quantized version of the NVIDIA Nemotron Nano VL V2 model, which is an auto-regressive vision language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Nemotron Nano VL FP4 QAD model is quantized with TensorRT Model Optimizer. This model was trained on commercial images for all three stages of training and supports single image inference. Use Cases: Image summarization. Text-image analysis, Optical Character Recognition, Interactive Q&A on images, Text Chain-of-Thought reasoning
NVIDIA-Nemotron-Nano-VL-12B-V2-FP4-QAD is the quantized version of the NVIDIA Nemotron Nano VL V2 model, which is an auto-regressive vision language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Nemotron Nano VL FP4 QAD model is quantized with TensorRT Model Optimizer. This model was trained on commercial images using Quantization-aware Distillation (QAD). This model was trained on commercial images for all three stages of training and supports single image inference.
NVIDIA-Nemotron-Nano-9B-v2 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. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model uses a hybrid architecture consisting primarily of Mamba-2 and MLP layers combined with just four Attention layers. For the architecture, please refer to the Nemotron-H tech report. The model was trained using Megatron-LM and NeMo-RL. The supported languages include: English, German, Spanish, French, Italian, and Japanese. Improved using Qwen.
NVIDIA-Nemotron-Nano-9B-v2-FP8 is a quantized version of NVIDIA-Nemotron-Nano-9B-v2 and 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. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model uses a hybrid architecture consisting primarily of Mamba-2 and MLP layers combined with just four Attention layers. For the architecture, please refer to the Nemotron-H tech report. Nano 9B v2 has 56 layers in total: 27 Mamba layers, 25 MLP layers, and 4 attention layers. In the FP8 quantized version, the Mamba and MLP layers are quantized to FP8, while all 4 attention layers and the Conv1d components within the Mamba layers are kept in BF16.
NVIDIA-Nemotron-Nano-9B-v2-NVFP4 is a quantized version of NVIDIA-Nemotron-Nano-9B-v2 and 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. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model uses a hybrid architecture consisting primarily of Mamba-2 and MLP layers combined with just four Attention layers. For the architecture, please refer to the Nemotron-H tech report. Nano 9B v2 has 56 layers in total: 27 Mamba layers, 25 MLP layers, and 4 attention layers. In the FP8/NVFP4 quantized version, the Mamba and MLP layers are quantized to FP8/NVFP4, while all 4 attention layers and the Conv1d components within the Mamba layers are kept in BF16. We used ModelOpt Post-training Quantization (PTQ) for both FP8 and NVFP4 quantization. For NVFP4, the first and last 2 layers are kept in BF16 to better preserve accuracy. On top of PTQ, Quantization-Aware Distillation (QAD) was also applied to NVFP4 for additional accuracy recovery.
NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information. Given a Red, Green, Blue (RGB) document image and a task prompt, the model produces formatted text and spatial annotations for document elements such as titles, paragraphs, captions, tables, charts, page headers, page footers, footnotes, pictures, and bibliography entries. Compared with NVIDIA Nemotron Parse v1.2, NVIDIA Nemotron Parse 2.0 adds an approximately 20k-token vocabulary expansion for more efficient multilingual support, chart-aware document parsing with the ` ` class token, and updated training coverage for chart/table-heavy documents. NVIDIA Nemotron Parse 2.0 is intended for document understanding, information retrieval, data extraction, and multimodal data-curation workflows. This model and its associated configuration files are licensed under the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). Use of the tokenizer included in this model is governed by the CC-BY-4.0 license. This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use. Contributions are accepted under the policy in CONTRIBUTING.md.
NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding. Given an image, NVIDIA Nemotron Parse v1.1 produces structured annotations, including formatted text, bounding-boxes and the corresponding semantic classes, ordered according to the document's reading flow. It overcomes the shortcomings of traditional OCR technologies that struggle with complex document layouts with structural variability, and helps transform unstructured documents into actionable and machine-usable representations. This has several downstream benefits such as increasing the availability of training-data for Large Language Models (LLMs), improving the accuracy of extractor, curator, retriever and AI agentic applications, and enhancing document understanding pipelines. **[Note]:** we recently released an updated Nemotron-Parse-v1.2 GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for NVIDIA AI Products. Use of this model is governed by the NVIDIA Open Model License Agreement. Use of the tokenizer included in this model is governed by the CC-BY-4.0 license.
