Qwen3-VL-30B-A3B-Instruct is a multimodal vision-language model based on the Qwen3-VL-30B model, which supports joint understanding and generation tasks of images and text. This model adopts an advanced vision-language fusion architecture and can handle complex multimodal reasoning tasks.

MultimodalGguf

LFM2-VL-3B is a multimodal vision-language model developed by Liquid AI, built on the LFM2 backbone architecture. It has powerful visual understanding and reasoning capabilities, especially excelling in fine-grained perception tasks. This model can efficiently process text and image inputs and supports native image processing with a resolution of up to 512×512.

MultimodalTransformersMultiple Languages

Qwen3-VL is the most powerful vision-language model in the Tongyi series, with comprehensive upgrades in text understanding and generation, visual perception and reasoning, context length, spatial and video understanding capabilities, etc., and it has excellent multimodal interaction capabilities.

MultimodalTransformers

Qwen3-VL-30B-A3B-Instruct-AWQ is a quantized version of the Qwen3-VL series, which has powerful visual language processing capabilities and supports tasks such as image understanding, video analysis, and multimodal reasoning. The model has significant improvements in text understanding, visual perception, spatial understanding, and long context processing.

MultimodalTransformers

This is the 4-bit quantized version of the Qwen3-VL-4B-Instruct model, specifically optimized for Apple Silicon chips and converted using the MLX framework. This model is a vision-language model that supports image understanding and multimodal dialogue tasks.

MultimodalMlx

Qwen3-VL is the most powerful vision-language model in the Tongyi large model series, with comprehensive upgrades in text understanding, visual perception, spatial understanding, video processing, etc., providing excellent multimodal capabilities.

MultimodalSafetensors

This is the 8-bit quantized version of the Qwen3-VL-4B-Instruct model in MLX format, converted by mlx-community. This model is a multimodal vision-language model with 4 billion parameters, supporting image understanding and text generation tasks, and optimized for instruction following scenarios.

MultimodalMlx

This is a visual language model in MLX format converted from the Qwen3-VL-30B-A3B-Thinking model, supporting image understanding and multimodal dialogue, and optimized with bf16 precision.

MultimodalMlx

The Ming-flash-omni preview version is a multimodal large model built on the Ling-Flash-2.0 sparse mixture of experts (MoE) architecture, with a total of 100B parameters and only 6B parameters activated per token. This model is a comprehensive upgrade based on Ming-Omni, showing significant improvements in multimodal understanding and generation, especially in speech recognition, image generation, and segmentation editing.

MultimodalDiffusersEnglish

Qwen3-VL-8B-Thinking is an 8-billion-parameter multimodal large language model developed by the Qwen team at Alibaba Cloud. It is designed for deep multimodal reasoning, supporting visual understanding, long context processing, and structured chain-of-thought generation, and performs excellently in complex reasoning tasks.

MultimodalMlx

This is the 4-bit quantized MLX format version of the Qwen3-VL-30B-A3B-Instruct model, converted and maintained by mlx-community. This model is a multimodal visual language model with 30 billion parameters, supporting image understanding and text generation tasks.

MultimodalMlx

Granite Docling 258M is an image-text to text model based on the ONNX format, specifically designed for document understanding and processing. This model can convert the document content in images into a structured text format and supports multimodal input processing.

MultimodalTransformers

Apriel-1.5-15B-Thinker is a 15-billion-parameter multimodal model designed for image understanding and reasoning. It uses the mid-term training method instead of RLHF training. This version is an MLX quantized version suitable for Apple chips, featuring low memory usage and fast startup speed.

MultimodalMlxEnglish

PaDT Pro 3B is a multimodal large language model based on Qwen2.5VL-3B. It adopts a unified paradigm of decodable block tokens and can directly generate text and visual outputs, achieving advanced performance in multiple visual perception and understanding tasks.

MultimodalTransformersMultiple Languages

Ming-UniVision is a large multimodal language model that first integrates continuous visual representations into the next-token prediction framework, unifying vision and language under a single autoregressive paradigm without discrete quantization or modality-specific heads. This model supports joint image understanding and generation, converges faster in vision-language training, and also supports multi-round context visual tasks.

MultimodalTransformersMultiple Languages

This is a vision-language model converted from the Huihui-GLM-4.5V-abliterated model, using the MXFP4 quantization format and specifically optimized for the Apple MLX framework. It supports image understanding and multimodal dialogue tasks.

MultimodalMlxMultiple Languages

UniPixel-3B is a unified multimodal large language model for pixel-level vision-language understanding, which can flexibly support various fine-grained tasks, including image/video segmentation, region understanding, and the novel PixelQA task. The model jointly requires object-centric reference, segmentation, and question answering in videos, achieving pixel-level visual reasoning capabilities.

MultimodalSafetensors

This project is based on the Qwen2.5-VL-7B-Instruct model and focuses on visual question answering tasks. It can accurately answer questions related to images and has high accuracy and relevance. This is a multimodal vision-language model that supports image understanding and image-based question-answering interactions.

MultimodalSafetensorsEnglish

ARC-Qwen-Video-7B is a multimodal model developed by Tencent ARC Laboratory for understanding real-world short videos. It is built on Qwen2.5-VL-7B-Instruct and supports the analysis and understanding of audio-video synchronization.

MultimodalTransformers

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