Qwen3-VL-2B-Thinking is one of the most powerful vision-language models in the Qwen series. It uses GGUF format weights and supports efficient inference on devices such as CPUs, NVIDIA GPUs, and Apple Silicon. This model has excellent multimodal understanding and reasoning capabilities, especially enhancing visual perception, spatial understanding, and agent interaction functions.

MultimodalTransformers

Qwen3-VL-4B-Instruct is one of the most powerful vision-language models in the Tongyi series. It has been comprehensively upgraded in text understanding, visual perception, spatial understanding, video processing, etc. It supports running on a variety of hardware devices and has excellent multimodal reasoning capabilities.

MultimodalTransformers

Gelato-30B-A3B is a state-of-the-art foundation model for GUI computer usage tasks. It is trained on the Click-100k dataset and outperforms previous specialized computer foundation models and larger vision-language models in multiple benchmark tests.

MultimodalTransformersEnglish

LightOnOCR-1B-1025 is a compact end-to-end vision-language model specifically designed for optical character recognition and document understanding. It achieves state-of-the-art accuracy at the same weight level, while being faster and less costly than large general-purpose vision-language models.

MultimodalSafetensorsMultiple Languages

VLA-Adapter is a micro vision-language-action model trained on Libero-Spatial. It adopts the Prismatic-VLM architecture and only uses Qwen2.5-0.5B as the large language model backbone. This model outperforms open-source VLA models with larger parameter scales in robot benchmarks, achieving high-performance vision-language-action understanding and execution.

MultimodalSafetensorsEnglish

Isaac-0.1 is the first open-source vision-language model launched by PerceptronAI. It has 2 billion parameters and is specifically designed for real-world applications. This model performs excellently in multimodal understanding and spatial reasoning, achieving performance that meets or exceeds models more than 50 times larger, setting a new efficiency standard.

MultimodalTransformers

FastVLM is an efficient visual encoding scheme for vision-language models. It significantly reduces the encoding time of high-resolution images through the innovative FastViTHD hybrid visual encoder, improving model performance and response speed, and performs excellently in multiple vision-language understanding benchmark tests.

MultimodalSafetensors

FastVLM is an efficient visual coding scheme designed specifically for vision-language models. Through the innovative hybrid visual encoder FastViTHD, it significantly reduces the encoding time of high-resolution images and improves the model's response speed and performance. This model performs excellently in multiple visual question-answering and document understanding benchmark tests.

MultimodalSafetensors

This is the quantized version of LiquidAI's LFM2-VL-1.6B model, which uses llama.cpp for imatrix quantization processing. It offers multiple quantization levels and can efficiently run vision-language models under different hardware conditions.

MultimodalGguf

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

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

LLaDA-V is a vision-language model based on the diffusion model, outperforming other diffusion multimodal large language models in performance.

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

A 7B-parameter open-source chart understanding vision-language model developed by Bespoke Labs, outperforming closed-source models like Gemini-1.5-Pro in chart QA tasks

MultimodalSafetensorsEnglish

A vision-language model specialized in describing anime-style images, fine-tuned from SmolVLM-500M-Base, trained on 180K synthetic image/caption pairs generated by large language models.

MultimodalSafetensorsEnglish

VLAA-Thinker is an innovative vision-language model that can process both image and text inputs simultaneously and generate high-quality text outputs. This model is developed based on the research results of the paper 'SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models' and focuses on R1-like reasoning abilities.

MultimodalTransformers

DeepSeer is a vision-language model developed based on the DeepSeek-R1 model, supporting chain-of-thought reasoning and trained through dialogue templates for visual models.

MultimodalTransformers

Eagle2 is a high-performance series of vision-language models focused on enhancing model performance through optimized data strategies and training methods. Eagle2-9B is the large model in this series, achieving a good balance between performance and inference speed.

MultimodalTransformersOther

Eagle 2 is a high-performance vision-language model family that focuses on transparency in data strategies and training schemes, aiming to drive the open-source community in developing competitive vision-language models.

MultimodalTransformersOther