NVIDIA Nemotron Parse v1.1 TC is an advanced document semantic understanding model that can extract text and table elements with spatial positioning from images and generate structured annotations, including formatted text, bounding boxes, and semantic categories. Compared with the previous version, the speed is increased by 20%, and the page order of unordered elements is retained.

MultimodalTransformers

NVIDIA Nemotron Parse v1.1 is an advanced document parsing model specifically designed to understand document semantics and extract text and table elements with spatial positioning. It can convert unstructured documents into machine-readable structured representations, overcoming the limitations of traditional OCR in handling complex document layouts.

MultimodalTransformers

NVIDIA Nemotron Nano v2 12B VL is a powerful multimodal vision-language model that supports multi-image reasoning and video understanding, and has document intelligence, visual question answering, and summarization capabilities. It can be used for commercial purposes.

MultimodalTransformers

Llama Nemotron Reranking 1B is a model developed by NVIDIA specifically for text retrieval reordering. It is fine-tuned based on the Llama-3.2-1B architecture and can provide a relevance log score for query-document pairs. It supports multilingual and long document processing.

Natural Language ProcessingTransformersOther

The Llama Nemotron Embedding 1B model is an embedding model developed by NVIDIA, optimized for multilingual and cross - language text question - answering retrieval. It supports 26 languages, can handle documents up to 8192 tokens long, and can significantly reduce data storage requirements through dynamic embedding sizes.

Natural Language ProcessingTransformersOther

Nemotron-Flash-3B is a new hybrid small language model launched by NVIDIA, specifically designed for low-latency requirements in practical applications. This model demonstrates excellent performance in tasks such as mathematics, coding, and common-sense reasoning, and also has the characteristics of excellent low latency for small batches and high throughput for large batches.

Natural Language ProcessingTransformers

This is a large language model with 49B parameters based on the NVIDIA Nemotron architecture. It has been converted to the MLX format and undergone 4-bit quantization, specifically optimized for Apple Silicon chips to provide efficient text generation capabilities.

Natural Language ProcessingTransformersEnglish

NVIDIA Nemotron Nano 9B v2 is a high-performance large language model developed by NVIDIA. It adopts the Mamba2-Transformer hybrid architecture, supports multilingual inference and chat tasks, and performs excellently in multiple benchmark tests. It especially supports the runtime 'thinking' budget control function.

Natural Language ProcessingTransformersMultiple Languages

NVIDIA Nemotron Nano 12B v2 is a large language model developed by NVIDIA, which adopts the Mamba2-Transformer hybrid architecture and has 12 billion parameters. This model supports multilingual processing, performs excellently in multiple benchmark tests, is particularly good at reasoning tasks, and supports runtime reasoning budget control.

Natural Language ProcessingTransformersMultiple Languages

NVIDIA Nemotron Nano 12B v2 is a large language model trained from scratch by NVIDIA, designed for both inference and non-inference tasks. It adopts a hybrid Mamba2-Transformer architecture, supports multiple languages, has controllable inference capabilities, and can generate inference processes or directly give answers according to user needs.

Natural Language ProcessingTransformersMultiple Languages

This is the GGUF quantized version of the NVIDIA Nemotron Nano 12B v2 model, which uses a hybrid Mamba - 2 and Transformer architecture, supports multilingual inference and chat functions, has 12 billion parameters, and supports a context length of up to 128K.

Natural Language ProcessingTransformersMultiple Languages

This is the Llamacpp imatrix quantization version of the NVIDIA Nemotron-Nano-12B-v2 model, offering a variety of quantization options, from BF16 to IQ2 quantization with extremely low bit rates, to help users run the model efficiently under different hardware conditions.

Natural Language ProcessingGguf

This is a quantized version of the NVIDIA Nemotron-H-47B-Reasoning-128K model, optimized using the imatrix technology of llama.cpp. The model supports a context length of 128K and is designed for reasoning tasks. It offers a variety of quantization options from BF16 to extremely low bitrates, suitable for different hardware configurations and performance requirements.

Natural Language ProcessingGguf

This is the Llamacpp imatrix quantization version of the NVIDIA Nemotron-H-8B-Reasoning-128K model, providing model files of various quantization types to meet the needs of different hardware and performance. It supports a context length of 128K and is optimized for reasoning tasks.

Natural Language ProcessingGguf

This is the quantized version of the NVIDIA Nemotron-Nano-9B-v2 model, which is quantized using the llama.cpp b6317 version. The model provides a variety of quantization options, including bf16, Q8_0, Q6_K_L, etc., suitable for different hardware and usage scenarios, making it convenient for users to deploy and use.

Natural Language ProcessingGguf

This is the 4-bit quantized version of the NVIDIA Nemotron Nano 9B v2 model, optimized for Apple Silicon and converted using the MLX framework. This model is a large language model with 9B parameters and supports multilingual text generation tasks.

Natural Language ProcessingMlxMultiple Languages

NVIDIA Nemotron Nano 12B v2 is a large language model trained from scratch by NVIDIA, designed for both inference and non-inference tasks. This model adopts a hybrid architecture that combines Mamba-2 and attention layers, supports multilingual processing, and can control inference capabilities through system prompts.

Natural Language ProcessingTransformersMultiple Languages

Jet - Nemotron - 4B is an efficient hybrid architecture language model launched by NVIDIA. It is built based on two core innovations: post - neural architecture search and the JetBlock linear attention module. In terms of performance, it surpasses open - source models such as Qwen3, Qwen2.5, Gemma3, and Llama3.2. At the same time, it achieves a maximum of 53.6 times acceleration in generation throughput on the H100 GPU.

Natural Language ProcessingTransformersEnglish

A quantized version of NVIDIA OpenReasoning - Nemotron - 32B, quantized through llama.cpp to reduce model storage and computational resource requirements for easy deployment.

Natural Language ProcessingGguf

This is the quantized version of NVIDIA OpenReasoning Nemotron 14B, with GGUF quantization provided by bartowski based on llama.cpp.

Natural Language ProcessingGguf