7

72B Qwen2.5 Kunou V1 GGUF

Developed by bartowski
Quantized version based on Qwen2.5-72B-Instruct, processed with llama.cpp for various quantization levels, suitable for local inference
Downloads 319
Release Time : 12/11/2024

Model Overview

This is a quantized version of a large language model with 72B parameters, supporting text generation tasks, built on the Qwen2.5 architecture, and adaptable to various hardware environments

Model Features

Multiple Quantization Options
Offers over 20 quantization versions from Q2 to Q8, catering to different hardware configurations and performance needs
imatrix Quantization
Uses llama.cpp's imatrix option for quantization to enhance quality
ARM Optimization
Provides optimized quantization versions specifically for ARM devices, supporting online weight repacking
High-quality Recommendations
Clearly labels recommended quantization versions to assist users in selection

Model Capabilities

Text Generation
Dialogue Systems
Instruction Following

Use Cases

Local AI Applications
Local Chat Assistant
Runs high-quality conversational AI on personal computers
Can operate smoothly in local environments like LM Studio
Content Creation
Used for generating various types of textual content
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase