Overview

QwQ-32B-Preview is an experimental large-scale research model by the Qwen Team, focusing on advanced AI reasoning. While it demonstrates strong analytical capabilities, it also presents notable limitations:

Variants

No Variant Cortex CLI command
1 gguf cortex run qwq

Use it with Jan (UI)

  1. Install Jan using Quickstart
  2. Use in Jan model Hub:
    cortexhub/qwq
    

Use it with Cortex (CLI)

  1. Install Cortex using Quickstart
  2. Run the model with command:
    cortex run qwq
    

Credits

  • Author: Qwen
  • Converter: [Homebrew]
  • Original License: [Licence]
  • Papers: [Paper]
Downloads last month
190
GGUF
Model size
32.8B params
Architecture
qwen2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.