OpenMMReasoner is a completely transparent two-stage multimodal reasoning solution, trained using supervised fine-tuning (SFT) and reinforcement learning (RL). A cold-start dataset of 874K samples was constructed in the SFT stage, and the RL stage used 74K samples to further enhance its capabilities, showing excellent performance in multimodal reasoning benchmark tests.

MultimodalTransformers

OpenMMReasoner is a fully transparent two-stage multimodal reasoning solution that covers supervised fine-tuning (SFT) and reinforcement learning (RL). By carefully constructing high-quality datasets, this solution surpasses powerful baseline models in multiple multimodal reasoning benchmark tests, laying a solid empirical foundation for future large-scale multimodal reasoning research.

MultimodalTransformers

This is a quantized version model based on Qwen3-VL-30B, specifically designed for image-text to text conversion tasks. The model optimizes the original model through quantization technology, providing a more efficient inference solution.

MultimodalGguf

SDXL-Deepfake-Detector is a tool for accurately detecting AI-generated faces. It focuses on maintaining the authenticity of the digital world and provides a privacy-protected and open-source solution to combat visual misinformation. This model achieves lightweight and highly accurate detection through fine-tuning a pre-trained model.

Computer VisionSafetensors

Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods in various scenarios, including short and long contexts, as well as reinforcement learning extension mechanisms. It can effectively solve the problem of low efficiency of traditional attention mechanisms in long context tasks and bring more efficient solutions to fields such as natural language processing.

Natural Language ProcessingTransformers

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-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

PixelWave is a text-to-image model developed based on Flux.1. It has been optimized through Nunchaku quantization (SVDQ), providing an efficient image generation solution for users with different GPU configurations.

Computer VisionDiffusersEnglish

This is the MXFP4_MOE quantized version of the DeepSeek-MoE-16B-Chat model, specifically optimized for text generation tasks, providing a more efficient inference solution.

Natural Language ProcessingGguf

bl00dsqibWan22-lora is a LoRA model trained based on the AI Toolkit by Ostris, specifically designed for image-to-video processing tasks, providing new solutions for the fields of image and video processing.

Computer VisionDiffusers

Frugal-Math-4B is a 4B parameter language model optimized for mathematical reasoning. It is trained using the Reinforcement Learning with Verification Reward (RLVR) method and can generate concise and verifiable mathematical solutions while maintaining high accuracy, significantly reducing the verbosity of reasoning.

Natural Language ProcessingTransformersMultiple Languages

This is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for the image-to-video conversion task, providing a new solution for image generation. This model is built on the Qwen/Qwen-Image base model, using 'John' as the trigger word to generate images.

MultimodalDiffusers

The Granite-4.0-h-Micro Model is a language model optimized based on the IBM Granite foundation model. It has undergone MLX quantization processing and is specifically optimized for Apple Silicon chips, providing efficient solutions for related applications.

Natural Language ProcessingTransformers

QuestA is an innovative framework that enhances the reasoning ability of large language models through a question-enhanced approach. It integrates partial solutions during the reinforcement learning training process, significantly improving the model's performance on complex tasks such as mathematical reasoning, especially achieving optimal results on small-parameter models.

Natural Language ProcessingTransformers

Klear is a large language model of Sparse Mixture of Experts (MoE) developed by the Kwai-Klear team of Kuaishou. It features high performance and inference efficiency. With a total of 46 billion parameters and only 2.5 billion activated parameters, it performs excellently in multiple capability benchmark tests, providing an efficient and powerful solution for practical applications.

Natural Language ProcessingTransformersMultiple Languages

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 the GGUF quantized version of the GPT-OSS-Code-Reasoning-20B model, optimized for efficient reasoning and reducing memory requirements. This model is specifically fine-tuned for competition programming and algorithm reasoning tasks, capable of generating Python/C++ solutions and reasoning processes.

Natural Language ProcessingGgufEnglish

TSLAM-15B is a 15-billion parameter telecom-specific language model developed by NetoAI Solutions. It is based on the Mixture-of-Experts (MoE) architecture and optimized for telecom domain expertise, advanced reasoning, and action-oriented workflows.

Natural Language ProcessingSafetensors

An Indian multilingual classification model optimized based on openai/whisper-small, supporting accurate identification of 23 Indian regional languages, providing an efficient solution for the field of language identification.

Audio ProcessingTransformersMultiple Languages