Melta is a unique small language model developed based on the Discord bot Melta27. It has a cute, charming, and enthusiastic personality, and is specifically designed to generate original, unique, and cute text content.

Natural Language ProcessingTransformersFrench

This is a static quantized version of the yanolja/YanoljaNEXT-Rosetta-27B-2511 model, providing weight files of various quantization types and supporting multilingual translation tasks. The model is specifically optimized for 32 languages, including major languages such as Chinese, English, Japanese, and Korean.

Natural Language ProcessingTransformersMultiple Languages

Qwen-Edit-Skin is a LoRA model fine-tuned based on the Qwen/Qwen-Image-Edit-2509 model, focusing on enhancing the realism and details of human skin in images and generating more natural and delicate skin textures.

Computer VisionDiffusers

Apollo-V0.1-4B-Thinking is a large language model based on 4B parameters, adopting a chain of thought reasoning architecture and specifically optimized for reasoning tasks. This model offers multiple quantization versions and can run efficiently in different hardware environments.

Natural Language ProcessingGguf

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

This is a quantized image-text-to-text model based on the Mistral architecture, with a parameter scale of 24B. It is specifically optimized and trained for instruction following tasks and supports multimodal input processing.

MultimodalGguf

Qwen3-VL is the most powerful vision-language model in the Tongyi series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, strong spatial and video dynamic understanding capabilities, and outstanding agent interaction capabilities.

MultimodalGguf

This is a quantized version of the Huihui Qwen3-VL-8B thinking ablated model. Based on the Qwen3-VL-8B architecture, it is specifically optimized and quantized for image-text conversion tasks and can be efficiently run through the llama.cpp tool.

MultimodalGguf

The quantized version of the Huihui Qwen3-VL-8B instruction ablation model, specifically designed for image-text to text conversion tasks. This model is based on the Qwen3-VL-8B architecture, optimized through instruction ablation and quantized, which can reduce the computational resource requirements while maintaining performance.

MultimodalGguf

The quantized version of the Huihui Qwen3-VL-4B thinking elimination model, optimized based on the Qwen3-VL-4B model, is specifically designed to eliminate the thinking chain reasoning process and can be used with the latest llama.cpp to provide efficient image-text to text processing capabilities.

MultimodalGguf

This is a quantized version based on the Huihui-Qwen3-VL-4B-Instruct-abliterated model, specifically designed for image-text to text conversion tasks. The model performance is optimized through quantization processing, providing support for multimodal applications.

MultimodalGguf

Qwen3-VL-32B-Thinking is the most powerful vision-language model in the Qwen series, with excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context processing, spatial and video dynamic understanding capabilities, and outstanding agent interaction capabilities.

MultimodalTransformers

Qwen3-VL-8B-Thinking is the most powerful vision-language model in the Tongyi Qianwen series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, strong spatial and video dynamic understanding capabilities, and outstanding agent interaction capabilities.

MultimodalGguf

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 dynamic understanding, and agent interaction capabilities. This model offers both dense architecture and mixture - of - experts architecture, supporting flexible deployment from edge devices to the cloud.

MultimodalTransformers

Qwen3-VL is the most powerful vision-language model in the Qwen series, achieving comprehensive upgrades in all aspects, including excellent text understanding and generation capabilities, deeper visual perception and reasoning capabilities, longer context length, enhanced spatial and video dynamic understanding capabilities, and stronger agent interaction capabilities.

MultimodalTransformers

This project performs 4-bit quantization on the MiniMax-M2 model using the DWQ (Dynamic Weight Quantization) method with the help of the mlx-lm library. This model is a lightweight version of MiniMax-M2, significantly reducing the model size while maintaining good performance.

Natural Language ProcessingMlx

MiniMax-M2 is a small Mixture of Experts (MoE) model built specifically for maximizing coding and agent workflows. It has a total of 230 billion parameters, with 1 billion active parameters. This model excels in coding and agent tasks while maintaining strong general intelligence. It is compact, fast, and cost-effective.

Natural Language ProcessingTransformers

The NeuTTS-Air Vietnamese Text-to-Speech Model is a high-quality Vietnamese voice synthesis model fine-tuned from the NeuTTS-Air base model based on more than 2.6 million Vietnamese audio samples. This model can achieve natural and fluent Vietnamese voice synthesis, support the voice cloning function, and is optimized for the production environment.

Audio ProcessingTransformersOther

This model is a violence detection model based on the VideoMAE architecture. After pre-training on the Kinetics dataset, it was fine-tuned for 92 rounds for the violence detection task. The model uses the Vision Transformer architecture and is specifically designed for video content analysis, capable of identifying violent behaviors in videos.

Computer VisionTransformers

QwenEdit InScene LoRAs is a group of models fine-tuned based on QwenEdit, focusing on enhancing the ability to generate images based on scene references. It includes two components, the InScene main model and InScene Annotate, which can create new scene shots while maintaining character consistency and scene coherence.

MultimodalDiffusers