Prima-24B is a large language model with 24 billion parameters, which is quantized and optimized through the GGUF format and specifically optimized for role-playing and creative writing tasks. This model is converted from the original Prima-24B model, using the Q4_K_M quantization level, which significantly reduces the model size and memory requirements while maintaining good performance.

Natural Language ProcessingGgufEnglish

This is a sentence transformer model fine-tuned based on sentence-transformers/all-mpnet-base-v2, which can map text to a 768-dimensional dense vector space and support various natural language processing tasks such as semantic similarity calculation, semantic search, and text classification.

Natural Language ProcessingSentence-transformers

This model is a fine-tuned version based on meta-llama/Llama-3.3-70B-Instruct. It is trained using the mlabonne/FineTome-100k dataset, which contains 100k token data. The model is fine-tuned using the Unsloth and Huggingface TRL libraries and supports English language processing.

Natural Language ProcessingTransformersEnglish

The aquif-3.5 series is the masterpiece released on November 3, 2025, including two versions, Plus and Max, which provide advanced inference capabilities and an unprecedented 1 million token context window, achieving state-of-the-art performance in their respective categories.

Natural Language ProcessingTransformersMultiple Languages

Aquif-3.5-Max-42B-A3B is a large language model with 42 billion parameters, which has undergone MXFP4_MOE quantization processing. It optimizes inference efficiency while maintaining high-quality text generation capabilities. This model is based on an advanced mixture-of-experts architecture and is suitable for various natural language processing tasks.

Natural Language ProcessingGguf

This is the MXFP4_MOE quantized version of the aquif-3.5-Plus-30B-A3B model. Through quantization technology, the model's resource occupancy is significantly reduced while maintaining similar performance, which has high engineering practice value.

Natural Language ProcessingGguf

This project is the MXFP4_MOE quantized version of the Kanana 1.5-15.7B-A3B instruction model, which can improve the model's operating efficiency in specific scenarios. This model is optimized based on kakaocorp/kanana-1.5-15.7b-a3b-instruct, using a mixture-of-experts architecture and MXFP4 quantization technology.

Natural Language ProcessingGguf

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

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

This is a quantized version of the Qwen3-VL-2B-Instruct model. The llama.cpp tool and the imatrix method are used to generate model files with multiple quantization levels, which are convenient for efficient operation in different hardware environments. This model is a multimodal vision-language model with 2B parameters, supporting the interaction between images and text.

MultimodalGguf

gpt-oss-safeguard-120b is a security reasoning model built by OpenAI based on gpt-oss, with 117 billion parameters (5.1 billion of which are active parameters). This model is specifically designed for security use cases and can classify text content and perform basic security tasks according to the provided security policies.

Natural Language ProcessingTransformers

This is an image text recognition model based on DeepSeek-OCR, which specifically solves the compatibility issues in the latest version of the transformers library, enabling the model to run smoothly in the latest versions such as transformers v4.57.1.

MultimodalTransformersEnglish

MiniMax-M2 6.5bit MLX is a quantized version based on the MiniMax-M2 model, which performs excellently in text generation tasks and supports multiple quantization levels. Among them, the q6.5bit quantization can achieve a perplexity of 1.128 in testing, which is comparable to q8.

Natural Language ProcessingMlx

TRELLIS Text XL is a large-scale 3D generation model, which is the text-conditioned version of TRELLIS with an XL model size. This model is proposed based on the paper 'Structured 3D Latents for Scalable and Versatile 3D Generation' and can generate high-quality 3D content according to text descriptions.

P1 - 30B - A3B is a large language model with 30 billion parameters. It has been processed by MXFP4_MOE quantization, which optimizes the inference efficiency while maintaining the model performance and is suitable for text generation tasks.

Natural Language ProcessingGguf

This is the MXFP4 quantized version of Qwen3-Next-80B-A3B-Thinking, which uses advanced quantization technology to significantly reduce storage and computational requirements while maintaining model performance. As an experimental version, it demonstrates the latest achievements in quantization technology.

Natural Language ProcessingGguf

olmOCR-2-7B-1025 is a high-quality OCR vision-language model developed by AllenAI, specifically designed to handle text recognition tasks in documents and images. This repository provides its GGUF quantized version, using the Q8_0 quantization method, which reduces the model size while maintaining excellent accuracy.

MultimodalGguf

LongCat-Video is a basic video generation model with 13.6 billion parameters, which performs excellently in generation tasks such as text-to-video, image-to-video, and video frame continuation. It is particularly good at efficient and high-quality long video generation.

MultimodalDiffusersMultiple Languages

This is a mixture-of-experts model based on the GLM-4.6 architecture. The REAP method was used to uniformly prune 40% of the experts. The model has 218B parameters and has been converted to a 3-bit quantization version in the MLX format, which is suitable for efficient operation on Apple chip devices.

Natural Language ProcessingTransformersEnglish

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. Through a unique two-stage architecture that combines a large language model with an efficient audio codec, it achieves low-latency and high-quality speech synthesis, with a real-time factor as low as 0.2, which is 5 times faster than real-time speed.

Audio ProcessingTransformersEnglish