Overview

Qwen2.5 by Qwen is a family of model include various specialized models for coding and mathematics available in multiple sizes from 0.5B to 72B parameters

Variants

No Variant Cortex CLI command
1 Qwen-2.5-0.5b cortex run qwen2.5:0.5b
2 Qwen-2.5-1.5b cortex run qwen2.5:1.5b
3 Qwen-2.5-3b cortex run qwen2.5:3b
4 Qwen-2.5-7b cortex run qwen2.5:7b
5 Qwen-2.5-14b cortex run qwen2.5:14b
6 Qwen-2.5-32b cortex run qwen2.5:32b
7 Qwen-2.5-72b cortex run qwen2.5:72b
8 Qwen-2.5-coder-1.5b cortex run qwen2.5:coder-1.5b
9 Qwen-2.5-coder-7b cortex run qwen2.5:coder-7b
10 Qwen-2.5-math-1.5b cortex run qwen2.5:math-1.5b
11 Qwen-2.5-math-7b cortex run qwen2.5:math-7b

Use it with Jan (UI)

  1. Install Jan using Quickstart
  2. Use in Jan model Hub:
    cortexso/qwen2.5
    

Use it with Cortex (CLI)

  1. Install Cortex using Quickstart
  2. Run the model with command:
    cortex run qwen2.5
    

Credits

Downloads last month
3,157
GGUF
Model size
494M 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.