This is a quantized version of TheDrummer's Magidonia-24B-v4.3 large language model. By using the imatrix quantization technology of llama.cpp, GGUF format files with various precisions from BF16 to IQ2_XS are generated, aiming to run the model more efficiently under different hardware conditions (especially in resource-constrained environments) while maintaining the model performance as much as possible.

Natural Language ProcessingGguf

This project is a quantized version of TheDrummer's Cydonia-24B-v4.3 model. It uses llama.cpp for quantization processing, aiming to provide model files of different quantization types to meet the needs of different hardware and performance. It is a large language model with 24B parameters, mainly used for text generation tasks.

Natural Language ProcessingGguf

Z-Image-Re-Turbo is a text-to-image generation model that has been optimized for de-reduction and re-acceleration based on the Z-Image-De-Turbo model. This model aims to balance the convenience during training and the speed during inference. It restores the fast generation ability close to the original Turbo model while maintaining the same training-friendly features as Z-Image-De-Turbo, enabling it to be perfectly compatible with a large number of trained LoRA models in the Z-Image ecosystem.

MultimodalDiffusers

Z-Image-Turbo is an image processing model quantized in FP8 E5M2 and E4M3FN formats. It is optimized based on the original Tongyi-MAI/Z-Image-Turbo model, significantly reducing the model size and inference resource requirements while maintaining performance.

MultimodalDiffusersEnglish

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

This repository contains a 4-step distilled model optimized for HunyuanVideo-1.5, which can achieve ultra-fast 4-step inference without using CFG (Classifier-Free Guidance), significantly reducing the generation time while maintaining high-quality video output.

MultimodalDiffusers

This is an MXFP4_MOE imatrix quantized version based on the Huihui-MiroThinker-v1.0-30B model, specifically optimized for text generation tasks. It significantly reduces the model size and inference cost while maintaining model performance.

Natural Language ProcessingGguf

Cecilia FT MS v1 is a Cuban language model fine-tuned based on Cecilia 2B v0.1, specifically optimized for Cuban Spanish to capture the nuances of Cuban language, culture, and society. This model supports Spanish and English and is mainly used for text generation tasks.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-Air-REAP-82B-A12B-mxfp4-mlx is a large language model with 82B parameters compressed by the REAP method based on the GLM-4.5-Air model. It uses the MXFP4 quantization format and is optimized for Mac devices, significantly reducing memory usage while maintaining the performance of core tasks.

Natural Language ProcessingMlxEnglish

This is a quantized version of ai-sage's GigaChat3-10B-A1.8B model, using the imatrix quantization technology of llama.cpp, which can run more efficiently under different hardware conditions. The model supports Russian and English and is mainly used for text generation tasks.

Natural Language ProcessingGgufMultiple Languages

Qsana-coder-base is a small language model (SLM) specifically designed for conceptual creativity in coding basics (Python, pseudo-code). It does not generate executable production code but rather generates coding logic snippets for educational and rapid prototyping scenarios. Its main goal is to stimulate the logical thinking and conceptual understanding of beginners.

Natural Language ProcessingTransformersFrench

This is an ablation version of Olmo-3-7B-Instruct, created using the Heretic tool. It quantifies the matrix by merging combined_en_small and harmful.txt, significantly reducing the model's rejection rate while maintaining a KL divergence of 0.

Natural Language ProcessingGguf

Atom-Olmo3-7B is a language model fine-tuned based on Olmo-3-7B-Instruct, specifically designed for collaborative problem-solving and creative exploration. This model can provide thoughtful and structured analysis when dealing with complex problems, while maintaining an engaging conversation style. It has an Apache 2.0 open-source license.

Natural Language ProcessingTransformersEnglish

A quantized model optimized for HunyuanVideo-1.5, used in conjunction with the LightX2V framework, which significantly reduces memory usage while maintaining high-quality video generation performance.

MultimodalDiffusers

This is the quantized version of kldzj's GPT-OSS-120B-Heretic-v2 model, which is quantized using the imatrix technology of llama.cpp. The model significantly reduces the storage and computing resource requirements through quantization technology while maintaining good model performance, facilitating deployment and operation on various devices.

Natural Language ProcessingGguf

UltraFlux is a diffusion transformer based on Flux, specifically designed for native 4K text-to-image generation. Through the collaborative design of data, architecture, and loss, it can maintain consistent image quality under various aspect ratios.

Computer VisionDiffusersEnglish

GLM-4.5-Iceblink-v2-106B-A12B-FP8 is a version based on the GLM-4.5-Iceblink-v2-106B-A12B model, using the most advanced mixture of experts quantization method for FP8 quantization. This model is specifically optimized for Ada, Hopper, or Blackwell series GPUs that support hardware FP8, significantly improving inference efficiency while maintaining high-quality output.

Natural Language ProcessingSafetensors

This is a quantized version based on the Huihui-MiroThinker-v1.0-8B model, specifically optimized for text generation tasks. It improves inference efficiency through quantization technology while maintaining the model's performance.

Natural Language ProcessingGguf

This is a version of the MiroThinker-v1.0-30B model quantized using MXFP4_MOE imatrix, implemented based on mradermacher's imatrix. This quantized model maintains the text generation ability of the original model while improving inference efficiency through quantization technology. It is suitable for various application scenarios that require efficient text generation.

Natural Language ProcessingGguf

This is the MXFP4_MOE quantized version of the MiniMax-M2-REAP-172B-A10B model, which is a memory-efficient compressed model. Through the REAP (Routing-Weighted Expert Activation Pruning) method, the model is compressed from 230B parameters to 172B parameters while maintaining performance, with a 25% reduction in size. It is suitable for resource-constrained environments, local deployment, and academic research.

Natural Language ProcessingGguf