This is a version of the Qwen3-Next-80B large language model after 4-bit quantization using Huawei's SINQ (Sinkhorn Normalized Quantization) method. SINQ is a novel, fast, and high-quality quantization method designed to significantly compress the model size (by approximately 75%) while maintaining almost the same accuracy as the original model, making it easier to deploy.

Natural Language ProcessingSafetensorsEnglish

VibeThinker-1.5B is a 1.5-billion-parameter dense language model launched by Weibo AI. It is fine-tuned based on Qwen2.5-Math-1.5B and is specifically designed for mathematical and algorithmic coding problems. Trained using the 'Spectrum to Signal Principle' framework, it outperforms larger models in multiple math competition tests. The training cost is approximately $7,800, and it supports an output of up to about 40k tokens.

Natural Language ProcessingTransformersMultiple Languages

This model is a knowledge distillation model based on the Qwen3-4B architecture, trained with approximately 54.4 million tokens generated by Gemini 2.5 Flash, aiming to integrate the behavior, inference process, and knowledge of Gemini-2.5 Flash into a single dataset.

Natural Language ProcessingTransformersEnglish

Qwen3-VL-2B-Thinking is a vision-language model launched by Qwen. Based on a 2B parameter scale, it uses MLX for 8-bit quantization and is specifically optimized for Apple Silicon chips. This model supports multimodal understanding and generation tasks for images and text.

MultimodalTransformers

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-2B-Instruct is the most powerful vision-language model in the Qwen series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, and strong spatial and video dynamic understanding abilities. This model uses a 2B parameter scale, supports instruction interaction, and is suitable for multimodal AI applications.

MultimodalTransformers

This is the MLX format conversion version of the Qwen3-Next-80B-A3B-Instruct model, optimized for efficient operation on Apple Silicon devices. The model is a large language model with 80 billion parameters, supporting text generation tasks and having powerful dialogue and reasoning capabilities.

Natural Language ProcessingMlx

This is the MXFP4_MOE quantized version of the Qwen3-VL-235B-A22B-Instruct model. Through specific quantization processing, the model performance is optimized, enabling the model to run more efficiently in resource-constrained environments and addressing the resource challenges in the deployment and application of large models.

MultimodalGguf

This project is the result of MXFP4_MOE quantization of the Qwen3-VL-30B-A3B-Thinking model. This model can achieve the conversion from image-text to text, providing a new solution for applications in related fields.

MultimodalGguf

This project is the result of MXFP4_MOE quantization on the Qwen3-VL-30B-A3B-Instruct model. This model can achieve the conversion from image text to text, providing a new solution for applications in related fields. As of October 22, 2025, this model is still in the experimental stage.

MultimodalGguf

Qwen3-VL-32B-Instruct is a powerful multimodal vision-language model developed based on the Qwen foundation model. After optimization and quantization, it is specifically optimized for Apple chip devices, providing efficient image-text processing capabilities.

MultimodalTransformers

Qwen3-VL-2B-Instruct is an efficient image-text-to-text model developed by the Qwen team. This model is optimized with MLX 8-bit quantization and is particularly suitable for Apple Silicon devices. It can handle visual language tasks and provide efficient solutions.

MultimodalTransformers

This is an MLX format version converted from the Qwen3-Coder-REAP-25B-A3B model, converted from the original model using the mlx-lm tool, specifically optimized for Apple Silicon chips, and supports efficient text generation tasks.

Natural Language ProcessingMlxEnglish

This is a LoRA model based on Qwen-Image-Edit-2509, specifically designed to accurately apply design patterns to people's shirts, providing new possibilities for image editing.

Computer VisionDiffusers

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-8B-Instruct is a multimodal vision-language model developed by the Qwen team, which supports the conversion from image-text to text. This version has undergone MLX 8-bit quantization processing and is specifically optimized for Apple silicon chips, improving the operating efficiency while maintaining performance.

MultimodalMlx

Qwen3-VL-8B-Instruct is a visual-language model developed by Qwen, optimized through MLX quantization, and specifically designed for Apple Silicon devices. This model supports multi-modal input of images and text, and can understand and generate text content related to images.

MultimodalMlx

Qwen3-VL-4B-Instruct is a 4-billion-parameter instruction-tuned multimodal large language model launched by the Alibaba Cloud Qwen team. It is optimized for Qualcomm NPUs, integrating powerful visual-language understanding capabilities with dialogue fine-tuning functions, and is suitable for practical application scenarios such as chat reasoning, document analysis, and visual dialogue.

MultimodalGguf

Qwen3-14B is a powerful language model that performs excellently in the field of text generation. This model has excellent general capabilities and offers an instruction variant that is friendly to fine-tuning, facilitating the further optimization and application of the model.

Natural Language ProcessingTransformers

This is the MLX format conversion version of the Qwen3-Omni-30B-A3B-Thinking model, converted using mlx-lm 0.28.1, and supports efficient operation on Apple Silicon devices.

Natural Language ProcessingMlxEnglish