GLM-4.1V-9B-Thinking is an open-source model developed based on the Vision-Language Model (VLM), aiming to explore the upper limit of the reasoning ability of vision-language models. By introducing the 'thinking paradigm' and reinforcement learning, it significantly improves the model's ability and reaches the leading level among VLMs with 10B parameters.

MultimodalTransformersMultiple Languages

GLM-4.1V-9B-Thinking is an open-source vision-language model based on the GLM-4-9B-0414 base model, specifically designed to explore the upper limit of the reasoning ability of vision-language models. It introduces the 'thinking paradigm' and uses reinforcement learning to significantly enhance its capabilities, performing excellently among VLMs with 10B parameters and rivaling or even surpassing models with larger parameters in multiple benchmark tasks.

MultimodalTransformersMultiple Languages

GLM-4.1V-9B-Thinking is a powerful vision-language model (VLM) that focuses on multimodal understanding and reasoning, and provides efficient inference capabilities through the AWQ quantization version.

MultimodalTransformers

GLM-4.1V-9B-Thinking is an open-source vision-language model based on the GLM-4-9B-0414 foundation model. By introducing the 'thinking paradigm' and reinforcement learning, the model's performance has been significantly improved, reaching a leading level among VLMs with 10 billion parameters. It has even surpassed the 72 billion parameter Qwen-2.5-VL-72B in 18 benchmark tasks.

MultimodalTransformersMultiple Languages

An image captioning vision-language model (VLM) freely open to the community, which can be used to train diffusion models and supports diverse image styles and content.

MultimodalTransformers

nanoVLM is a lightweight vision-language model (VLM) designed for efficient training and experimentation.

MultimodalSafetensors

nanoVLM is a lightweight vision-language model (VLM) designed for efficient training and experimentation.

MultimodalSafetensors

FlashVL is a new approach to optimizing vision-language models (VLMs) for real-time applications, aiming to achieve ultra-low latency and high throughput without sacrificing accuracy.

MultimodalTransformersMultiple Languages

nanoVLM is an ultra-minimalist lightweight vision-language model (VLM) designed for efficient training and experimentation.

MultimodalSafetensors

VLM2Vec-V2 is a model for large-scale multimodal embedding tasks. By training a vision-language model, it provides more powerful embedding capabilities for multimodal data such as videos, images, and visual documents.

MultimodalTransformersEnglish

Trillion-LLaVA-7B is a vision-language model (VLM) capable of understanding images, developed based on the Trillion-7B-preview foundation model.

MultimodalTransformersMultiple Languages

Eagle 2.5 is a cutting-edge vision-language model (VLM) designed for long-context multimodal learning, supporting the processing of video sequences up to 512 frames and high-resolution images.

MultimodalTransformersOther

A Japanese Vision-Language Model (VLM) developed by NABLAS, supporting image, multi-image, and video inputs, suitable for various multimodal tasks.

MultimodalTransformersJapanese

A vision-language model based on Qwen2.5-VL-3B-Instruct, enhanced with mathematical capabilities and trained using VLM-R1 reinforcement learning, specializing in solving math-related visual question answering tasks.

MultimodalSafetensorsEnglish

Poseless-3B is a vision-language model (VLM)-based robotic hand control framework that directly maps 2D images to joint angles without explicit pose estimation.

MultimodalTransformers

A vision-language model based on Qwen2.5-VL-3B-Instruct, enhanced with VLM-R1 reinforcement learning, focusing on referring expression comprehension tasks.

MultimodalSafetensorsEnglish

Asagi-8B is a large-scale Japanese Vision-Language Model (VLM) trained on extensive Japanese datasets, integrating diverse data sources.

MultimodalTransformersJapanese

Asagi-4B is a large-scale Japanese Vision-Language Model (VLM) trained on extensive Japanese datasets, incorporating diverse data sources.

MultimodalTransformersJapanese

Eagle2-9B is the latest Vision-Language Model (VLM) released by NVIDIA, achieving a perfect balance between performance and inference speed. It is built on the Qwen2.5-7B-Instruct language model and the Siglip+ConvNext vision model, supporting multilingual and multimodal tasks.

MultimodalTransformersOther

MiniVLA is a more compact yet higher-performing vision-language-action model, compatible with the Prismatic VLMs project codebase.

MultimodalTransformersEnglish