You have to use the backend from HimariO's branch. Big thanks to add Qwen2.5VL support! Additional discussions

'Make knowledge free for everyone'

GGUF

Model size

0.7B params

Architecture

clip

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DevQuasar/Qwen.Qwen2.5-VL-7B-Instruct-GGUF

Base model

Quantized

(136)

this model

Collections including DevQuasar/Qwen.Qwen2.5-VL-7B-Instruct-GGUF