Qwen3 235B A22B Exl2
Exllamav2 quantized version of Qwen3-235B-A22B, offering multiple quantization precision options, suitable for efficient text generation tasks.
Downloads 53
Release Time : 5/2/2025
Model Overview
Exllamav2 quantized version based on the Qwen3-235B-A22B large language model, supporting quantization configurations with different bit widths, suitable for text generation scenarios requiring efficient inference.
Model Features
Multi-precision Quantization Support
Offers three quantization precision options: 2.25bpw, 3.00bpw, and 4.00bpw, meeting precision and efficiency requirements for different scenarios
Efficient Inference
Achieves more efficient large model inference through Exllamav2 quantization technology
Cutting-edge Technical Support
Utilizes the latest quantization technology from the Exllamav2 development branch (commit 68976a0)
Model Capabilities
Text Generation
Large Language Model Inference
Use Cases
Text Generation
Content Creation
Used for automatically generating articles, stories, and other content
Dialogue Systems
Building intelligent conversational assistants
Featured Recommended AI Models
Š 2025AIbase