Qwen2.5-32B-Instruct-GPTQ-Int4

Name: Qwen2.5-32B-Instruct-GPTQ-Int4
Author: Qwen

32B open-weight LLM by Qwen

Live

Open / InstallLast updated August 5, 2026

Description

Qwen2.5-32B-Instruct-GPTQ-Int4 is an open-weight text-generation model with roughly 32B parameters published by Qwen on the Hugging Face Hub. It has 491,706 downloads. Runs with transformers.

Author

Qwen

Platform

api

Pricing model

free

Capabilities

Text generation
Conversational
Library: transformers
32B parameters

Benchmarks

No benchmark results have been added yet.