This is the GGUF quantized version of the large language model Mistral-Large-3-675B-Instruct-2512 developed by Mistral AI. The original model has 675 billion parameters and is designed for instruction-following tasks. This project uses the llama.cpp tool and combines it with the imatrix calibration dataset to generate more than 20 different precision quantized model files from Q8_0 to IQ1_S, aiming to balance model performance, inference speed, and storage/memory usage, enabling it to run on a wider range of hardware.

Natural Language ProcessingGgufMultiple Languages

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

This is a 6-bit quantized version converted from the Kimi-Linear-48B-A3B-Instruct model, optimized for the Apple MLX framework. The model retains the powerful instruction-following ability of the original model, while significantly reducing storage and computational requirements through quantization technology, making it suitable for efficient operation on Apple hardware.

Natural Language ProcessingMlx

This is a quantized version of the internlm's JanusCoder-8B model, using the imatrix quantization technology of llama.cpp. It significantly reduces the storage and computational resource requirements of the model while ensuring performance, enabling the model to run efficiently on more devices.

Natural Language ProcessingGguf

This is the MXFP4_MOE quantized version of the Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL model, specifically optimized for text generation tasks. The model is based on a large language model architecture with 42B parameters. Through quantization technology, it reduces the computational and storage requirements while maintaining good performance.

Natural Language ProcessingGguf

GLM-4.6 AWQ - INT4 is a 4-bit quantized version of the GLM-4.6 model, using the AWQ quantization method. It significantly reduces the storage and computing resource requirements while maintaining the model's performance. This model supports a 200K context length and shows significant improvements in coding, reasoning, and agent tasks compared to GLM-4.5.

Natural Language ProcessingTransformersMultiple Languages

This is the MXFP4_MOE quantized version of the Huihui GPT-OSS-120B-BF16-abliterated-v2 model, specifically optimized for text generation tasks to provide efficient text generation capabilities. The model reduces computational and storage requirements through quantization techniques while maintaining good performance.

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

This is the MXFP4_MOE quantized version of the Qwen3-Coder-REAP-25B-A3B model, specifically designed for text generation tasks. This model is based on the 25B parameter Qwen3-Coder architecture, and the storage and inference efficiency are optimized through the MXFP4 quantization technology while maintaining good performance.

Natural Language ProcessingGguf

Qwen3-VL-32B-Instruct AWQ - INT4 is a 4-bit quantized version based on the Qwen3-VL-32B-Instruct base model. It uses the AWQ quantization method, significantly reducing storage and computing resource requirements while maintaining performance. This is the most powerful vision-language model in the Qwen series, with comprehensive upgrades in text understanding, visual perception, context length, etc.

MultimodalTransformers

This is a quantized version of the Qwen3-Coder-REAP-25B-A3B model from Cerebras. It uses the imatrix technology of llama.cpp for quantization, which can reduce the model storage space and computational resource requirements while maintaining the model performance.

Natural Language ProcessingGguf

This is a Q4_0 quantized version based on the Qwen3-Next-80B-A3B-Instruct model. Through specific quantization techniques, the efficiency of the model in storage and computation has been significantly improved while maintaining good performance.

Natural Language ProcessingGguf

The Llama Nemotron Embedding 1B model is an embedding model developed by NVIDIA, optimized for multilingual and cross - language text question - answering retrieval. It supports 26 languages, can handle documents up to 8192 tokens long, and can significantly reduce data storage requirements through dynamic embedding sizes.

Natural Language ProcessingTransformersOther

A high-performance video generation model with 4-step reasoning based on LoRA. The LoRA weights are extracted from the Wan2.2 distilled model, featuring flexible deployment, efficient storage, and excellent generation quality.

MultimodalDiffusers

This is a quantized version of the Qwen3-VL-4B-Thinking model. Through the imatrix quantization method of llama.cpp, it significantly reduces the model storage and computational resource requirements while ensuring performance, and supports deployment and use in various hardware environments.

MultimodalGguf

This is a version after quantizing Qwen/Qwen3-Next-80B-A3B-Thinking using LLM Compressor and the NVFP4 format. It adopts the FP4 micro-scaling technology, significantly reducing model storage and computational requirements while maintaining high precision.

Natural Language ProcessingTransformersMultiple Languages

This is the GGUF quantized version of the IBM Granite-4.0-H-Tiny model, which uses llama.cpp for multi-precision quantization processing. While ensuring performance, it significantly reduces the model storage space and computational resource requirements, facilitating deployment and operation.

Natural Language ProcessingGguf

This project provides a quantized version of Tencent's Hunyuan-MT-7B large language model. Through model compression technology, it reduces the computing and storage requirements, aiming to make knowledge accessible to everyone and make high-performance AI models more popular and user - friendly.

Natural Language ProcessingGguf

Apertus-8B-Instruct-2509-NVFP4 is an NVFP4 quantized version based on swiss-ai/Apertus-8B-Instruct-2509, generated by the llmcompressor tool. This model significantly reduces storage space and computational resource requirements while maintaining performance, improving inference efficiency.

Natural Language ProcessingSafetensorsEnglish

This is a quantized version of TheDrummer's Behemoth R1 123B v2 model, quantized using llama.cpp and imatrix technology. It can significantly reduce model storage space and computational resource requirements while maintaining good performance, making it suitable for running on different devices.

Natural Language ProcessingGguf