Inference:

./llama-qwen2vl-cli -m Q8_0.gguf --mmproj qwen2vl-vision.gguf -p "Describe this image." --image "demo.jpg"

Converted using this Colab Notebook:

Colab Notebook

Special Thanks to:

HimariO for the excellent work on enabling quantization for Qwen2-VL! PR on GitHub

Downloads last month
82
GGUF
Model size
1.54B params
Architecture
qwen2vl

4-bit

8-bit

16-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.

Model tree for Lyte/Qwen2-VL-2B-Instruct-GGUF

Base model

Qwen/Qwen2-VL-2B
Quantized
(37)
this model