NVLM 1.0

Cutting-edge multimodal large language model

CommonProductProductivityMultimodalLarge Language Model

NVLM 1.0 is part of the cutting-edge series of multimodal large language models launched by NVIDIA ADLR, achieving industry-leading performance in visual-language tasks, comparable to top proprietary and open-access models. This model improves accuracy in pure text tasks following multimodal training. The open-source model weights and Megatron-Core training code offer valuable resources for the community.

Achieves industry-leading performance in visual-language tasks.
Improves accuracy in pure text tasks after multimodal training.
Provides open-source model weights and training code for community use and research.
Achieves top scores in benchmarks such as OCRBench and VQAv2.
Demonstrates exceptional instruction-following abilities and image captioning capabilities in multimodal tasks.
Understands humor behind images
performs OCR text label recognition
and reasons about humor.
Executes mathematical reasoning and coding based on visual information.

\NVLM 1.0 is designed for researchers and developers who need to process large amounts of visual and linguistic data
particularly in the fields of machine learning
artificial intelligence
and data science. It aids users in achieving breakthroughs in image recognition
natural language processing

Used for image captioning
improving accuracy in understanding image content.
Provides step-by-step mathematical reasoning in problem-solving for mathematics and programming.
Employed for OCR tasks
recognizing and processing text within images.

Visit the official NVIDIA ADLR website to download the model weights and training code for NVLM 1.0.
Read the documentation to understand the model architecture and usage.
Fine-tune the model as needed to adapt it to specific visual-language tasks.
Train the model using the Megatron-Core training code.
Utilize the model for tasks such as image captioning

Visit

NVLM 1.0 Visit Over Time

Monthly Visits

268002

Bounce Rate

63.06%

Page per Visit

1.9

Visit Duration

00:00:53

NVLM 1.0 Visit Trend

NVLM 1.0 Visit Geography

NVLM 1.0 Traffic Sources

NVLM 1.0 Alternatives

VITA-1.5 — VITA-1.5: A GPT-4o level multimodal large language model for real-time visual and speech interaction.

Programming•Multimodal•Large Language Model

270

Valley 2.0 — A multimodal large language model that enhances the ability to process text, image, and video data.

Others•Multimodal•Large Language Model

240

Goedel-Prover — Goedel-Prover is an open-source automated theorem proving model focused on the formal verification of mathematical problems.

Programming•Automated Theorem Proving•Mathematics

OmniParser-v2.0 — OmniParser is a versatile screen parsing tool that converts UI screenshots into a structured format, improving the performance of LLM-based UI agents.

Image•Screen Parsing•Image Recognition

588

Mistral-Small-24B-Instruct-2501 — Mistral Small 24B is a multilingual, high-performance instruction-tuned large language model suitable for various application scenarios.

Productivity•Large Language Model•Multilingual

MNN Large Model Android App — A fully functional Android app supporting multimodal capabilities with a large language model.

Productivity•Large Language Model•Multimodal

2262

SmolVLM-500M-Instruct — SmolVLM-500M is a lightweight multimodal model capable of processing image and text inputs to generate text outputs.

Image•Multimodal•Image Description

DeepSeek-R1-Distill-Llama-70B — DeepSeek-R1-Distill-Llama-70B is a large language model optimized using reinforcement learning, focusing on reasoning and conversational capabilities.

Programming•Large Language Model•Reinforcement Learning

654

InternVL2_5-78B-MPO — This is an advanced series of multimodal large language models that demonstrate outstanding overall performance.

Productivity•Multimodal•Large Language Model

132

InternLM3-8B-Instruct — InternLM3-8B-Instruct is an open-source instruction model with 8 billion parameters designed for general-purpose use and advanced reasoning.

Programming•Large Language Model•Open Source

InternVL2_5-38B-MPO — The InternVL2.5-MPO series models are based on InternVL2.5 and Hybrid Preference Optimization, showcasing exceptional performance.

chatting•Multimodal•Large Language Model

198

InternVL2_5-26B-MPO-AWQ — An advanced multimodal large language model with exceptional reasoning capabilities.

Programming•Multimodal•Large Language Model

InternVL2_5-26B-MPO — A multimodal large language model that enhances the interaction between visual and linguistic data.

Image•Multimodal•Large Language Model

126

InternVL2_5-8B-MPO-AWQ — A multimodal large language model enhancing visual and linguistic interaction capabilities.

Image•Multimodal•Large Language Model

InternVL2_5-8B-MPO — A large multimodal language model showcasing exceptional overall performance.

Image•Multimodal•Large Language Model

228

HuatuoGPT-o1-8B — An advanced large language model for the medical field.

Others•Healthcare•Reasoning

HuatuoGPT-o1 — A large language model for complex reasoning in the medical field

Education•Medical•Complex Reasoning

204

InternVL2_5-4B-MPO-AWQ — A multimodal large language model designed to enhance image and text interaction capabilities.

Image•Multimodal•Large Language Model

OpenEMMA — An open-source end-to-end multimodal model for autonomous driving.

Productivity•Autonomous Driving•End-to-End Model

126

InternVL2_5-4B-MPO — A multimodal large language model demonstrating exceptional overall performance.

Image•Multimodal•Large Language Model

InternVL2_5-2B-MPO — Advanced multimodal large language model

Image•Multimodal•Large Language Model

InternVL2_5-1B-MPO — A multimodal large language model that enhances integrated understanding of visual and language data.

Productivity•Multimodal•Large Language Model

168

InternVL2-8B-MPO — Multimodal large language model, enhancing multimodal inference capabilities.

Productivity•multimodal•large language model

Gemini Multimodal Live + WebRTC — A single-file application that integrates Gemini's multimodal live streaming and WebRTC technology.

Programming•WebRTC•Gemini

138

InternVL 2.5 — Open-source multimodal large language model series

Productivity•multimodal•large language model

144

InternVL2_5-4B — A multimodal large language model that integrates visual and language understanding.

Image•Multimodal•Large Language Model

InternVL2_5-2B — A multimodal large language model that supports deep interaction between images and text.

Image•Multimodal•Large Language Model

InternVL2_5-1B — A large multimodal language model that supports image and text understanding.

Image•Multimodal•Large Language Model

144

InternVL2_5-8B — A multimodal large language model supporting interaction understanding between images and text.

Image•Multimodal•Large Language Model

180

Best AI Websites & Tools

NVLM 1.0

NVLM 1.0 Visit Over Time

NVLM 1.0 Visit Trend

NVLM 1.0 Visit Geography

NVLM 1.0 Traffic Sources

NVLM 1.0 Alternatives

VITA-1.5 — VITA-1.5: A GPT-4o level multimodal large language model for real-time visual and speech interaction.

Valley 2.0 — A multimodal large language model that enhances the ability to process text, image, and video data.

Goedel-Prover — Goedel-Prover is an open-source automated theorem proving model focused on the formal verification of mathematical problems.

OmniParser-v2.0 — OmniParser is a versatile screen parsing tool that converts UI screenshots into a structured format, improving the performance of LLM-based UI agents.

Mistral-Small-24B-Instruct-2501 — Mistral Small 24B is a multilingual, high-performance instruction-tuned large language model suitable for various application scenarios.

MNN Large Model Android App — A fully functional Android app supporting multimodal capabilities with a large language model.

SmolVLM-500M-Instruct — SmolVLM-500M is a lightweight multimodal model capable of processing image and text inputs to generate text outputs.

DeepSeek-R1-Distill-Llama-70B — DeepSeek-R1-Distill-Llama-70B is a large language model optimized using reinforcement learning, focusing on reasoning and conversational capabilities.

InternVL2_5-78B-MPO — This is an advanced series of multimodal large language models that demonstrate outstanding overall performance.

InternLM3-8B-Instruct — InternLM3-8B-Instruct is an open-source instruction model with 8 billion parameters designed for general-purpose use and advanced reasoning.

InternVL2_5-38B-MPO — The InternVL2.5-MPO series models are based on InternVL2.5 and Hybrid Preference Optimization, showcasing exceptional performance.

InternVL2_5-26B-MPO-AWQ — An advanced multimodal large language model with exceptional reasoning capabilities.

InternVL2_5-26B-MPO — A multimodal large language model that enhances the interaction between visual and linguistic data.

InternVL2_5-8B-MPO-AWQ — A multimodal large language model enhancing visual and linguistic interaction capabilities.

InternVL2_5-8B-MPO — A large multimodal language model showcasing exceptional overall performance.

HuatuoGPT-o1-8B — An advanced large language model for the medical field.

HuatuoGPT-o1 — A large language model for complex reasoning in the medical field

InternVL2_5-4B-MPO-AWQ — A multimodal large language model designed to enhance image and text interaction capabilities.

OpenEMMA — An open-source end-to-end multimodal model for autonomous driving.

InternVL2_5-4B-MPO — A multimodal large language model demonstrating exceptional overall performance.

InternVL2_5-2B-MPO — Advanced multimodal large language model

InternVL2_5-1B-MPO — A multimodal large language model that enhances integrated understanding of visual and language data.

InternVL2-8B-MPO — Multimodal large language model, enhancing multimodal inference capabilities.

Gemini Multimodal Live + WebRTC — A single-file application that integrates Gemini's multimodal live streaming and WebRTC technology.

InternVL 2.5 — Open-source multimodal large language model series

InternVL2_5-4B — A multimodal large language model that integrates visual and language understanding.

InternVL2_5-2B — A multimodal large language model that supports deep interaction between images and text.

InternVL2_5-1B — A large multimodal language model that supports image and text understanding.

InternVL2_5-8B — A multimodal large language model supporting interaction understanding between images and text.