InternVL3.5-4B is a medium-scale version in the open-source multimodal model series, achieving significant progress in generality, reasoning ability, and reasoning efficiency, and supporting new capabilities such as GUI interaction. The model adopts a cascaded reinforcement learning framework and visual resolution router technology to achieve efficient multimodal understanding and reasoning.

MultimodalTransformersOther

InternVL3_5-38B is a member of the open-source multimodal model InternVL3.5 series, which has made significant progress in versatility, reasoning ability, and reasoning efficiency. It supports multiple languages and can be applied to image-text-to-text tasks. It uses a cascaded reinforcement learning framework and visual resolution router technology to optimize performance.

MultimodalTransformersOther

InternVL3.5-14B is an open-source multimodal model in the InternVL series, which significantly improves generality, reasoning ability, and reasoning efficiency, supports new functions such as GUI interaction, and narrows the performance gap with commercial models.

MultimodalTransformersOther

InternVL3.5-1B is an open-source multimodal model in the InternVL series, with a parameter count of 1.1B, including 0.3B visual parameters and 0.8B language parameters. This model significantly improves generality, reasoning ability, and reasoning efficiency, and supports new functions such as GUI interaction.

MultimodalTransformersOther

InternVL3.5-4B is a medium-scale version of the open-source multimodal model series, containing 470 million parameters. It adopts an advanced cascaded reinforcement learning framework and visual resolution router technology, significantly improving the multimodal reasoning ability and efficiency.

MultimodalTransformersOther

InternVL3.5 is a new member of the open-source multimodal model family, significantly improving the versatility, reasoning ability, and reasoning efficiency of the InternVL series. It supports new functions such as GUI interaction and reaches the advanced level of open-source multimodal large language models.

MultimodalTransformersOther

This is the FP8 dynamic (W8A8) quantization version of OpenGVLab/InternVL3_5-8B, optimized for high-performance inference with vLLM. It uses FP8 dynamic quantization technology to significantly reduce memory usage and improve inference speed while maintaining visual understanding capabilities.

MultimodalSafetensorsMultiple Languages

This is the FP8 dynamic quantization version of the InternVL3_5-GPT-OSS-20B-A4B-Preview model, optimized with w8a8 technology, specifically designed for high-performance inference deployment on vLLM. While maintaining visual language understanding capabilities, this model significantly improves inference speed and memory efficiency.

MultimodalSafetensorsMultiple Languages

This is the FP8 dynamic (W8A8) quantized version of OpenGVLab/InternVL3_5-30B-A3B, optimized for high-performance inference with vLLM. It uses FP8 dynamic quantization technology, reducing memory usage by approximately 50% and significantly improving inference speed.

MultimodalSafetensorsOther

InternVL3_5-38B-Q8_0-GGUF is a GGUF quantized version converted from OpenGVLab's InternVL3_5-38B model through llama.cpp. This model is a multimodal vision-language model with 38B parameters, supporting the joint understanding and generation of images and text. It uses the Q8_0 quantization format to optimize inference efficiency.

MultimodalTransformersOther

This is a quantized version of the InternVL3_5 14B model from OpenGVLab, which supports image-text to text conversion tasks. The model's operating efficiency is improved through quantization technology, providing a more efficient solution for related applications.

MultimodalGguf

This is the GGUF quantized version of the InternVL3_5 8B model released by OpenGVLab, specifically designed for image-text to text conversion tasks. It provides a more efficient inference solution through quantization technology.

MultimodalGguf

This is a multimodal vision-language model based on the InternVL3 architecture, quantized into the GGUF format. It supports the conversion from image-text to text and has multilingual capabilities.

MultimodalTransformersOther

This is an unrestricted version model fine-tuned based on InternVL3-8B, converted to the GGUF format, supporting multilingual image-text to text tasks, and suitable for a wider range of usage scenarios.

MultimodalTransformersOther

This is the FP8 static quantization version of OpenGVLab/InternVL3-38B, optimized for high-performance inference using vLLM. It achieves approximately 2x acceleration on vision-language tasks with minimal accuracy loss.

MultimodalSafetensorsMultiple Languages

InternVL3 - 78B - Instruct is an advanced multimodal large language model that performs excellently in multimodal perception, reasoning, and language processing. Through the native multimodal pre - training method, this model integrates visual and language learning into a unified training stage and demonstrates outstanding capabilities in multiple fields such as tool use, GUI agents, industrial image analysis, and 3D visual perception.

MultimodalTransformersOther

InternVL3-38B-Instruct is an advanced Multimodal Large Language Model (MLLM) that demonstrates exceptional overall performance, with strong multimodal perception and reasoning capabilities.

MultimodalTransformersmultilingual

InternVL3-8B-Instruct is an advanced multimodal large language model (MLLM) that demonstrates exceptional overall performance, with strong multimodal perception and reasoning capabilities.

MultimodalTransformersmultilingual

InternVL3-14B-Instruct is an advanced Multimodal Large Language Model (MLLM) that demonstrates exceptional multimodal perception and reasoning capabilities, supporting various tasks such as tool usage, GUI agents, industrial image analysis, and 3D visual perception.

MultimodalTransformersmultilingual

InternVL3-78B is an advanced multimodal large language model with excellent multimodal perception and reasoning capabilities. It performs outstandingly in fields such as tool use, GUI agents, industrial image analysis, and 3D visual perception, and also has very good overall text performance.

MultimodalTransformersOther