# High-Precision Quantization

Qwen3 is the latest generation of large language models in the Tongyi Qianwen series, offering a complete suite of dense models and Mixture of Experts (MoE) models. Based on large-scale training, Qwen3 has achieved breakthrough progress in reasoning capabilities, instruction following, agent functionalities, and multilingual support.

Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a range of dense and mixture of experts (MoE) models. Based on large-scale training, Qwen3 has achieved breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.

A quantized version of the Qwen2.5-VL-72B-Instruct multimodal large language model, supporting image-text-to-text tasks, suitable for various quantization levels from high precision to low memory requirements.

A quantized version of Qwen2.5-VL-7B-Instruct, using llama.cpp for quantization, supporting multimodal tasks such as image-to-text conversion.

This is the quantized version of the NVIDIA OpenCodeReasoning-Nemotron-32B-IOI model, processed using llama.cpp for quantization, suitable for code reasoning tasks.

This is the quantized version of the nomic-ai/nomic-embed-code model, using llama.cpp for imatrix quantization, suitable for code embedding and feature extraction tasks.

The Nomic code embedding model is a top-tier code retrieval tool that supports multiple programming languages and excels in code retrieval tasks.

This model is a GGUF format version converted from Gemma-3-27b-tools, suitable for local inference tasks.

This is a quantized version based on the mlabonne/gemma-3-4b-it-abliterated model, using llama.cpp for imatrix quantization, suitable for image-text-to-text tasks.

A quantized version based on Google Gemma 3B model, optimized using llama.cpp, supporting multiple quantization levels, suitable for text generation tasks.

Gemma-3-12b-it is a large language model developed by Google, based on the transformer architecture, focusing on text generation tasks.

Quantized version of OlympicCoder-32B, based on llama.cpp's imatrix quantization method, suitable for code generation tasks.

A 32B-parameter large language model based on llama.cpp, specializing in text generation tasks for chemistry, biology, climate, and medical fields

QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities. This repository provides its AWQ 4-bit quantized version.

Qwen2-VL-2B-Instruct is a multimodal vision-language model that supports image-text generation tasks, based on the Qwen2 architecture with a parameter scale of 2B.

A GGUF-format T5 model for grammar and spelling correction, supporting high-precision quantization versions to ensure correction quality.

This is a GGUF-format quantized version of the beomi/OPEN-SOLAR-KO-10.7B model, supporting 2-8 bit quantization levels, suitable for Korean and English text generation tasks.