gemma-3-4b-ov

gemma-3-4b-ov is an OpenVino int4 quantized version of gemma-3-4b, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

This is a vision-to-text model from the Google Gemma 3 series and is a very high-quality innovative small model that accepts multi-modal inputs (image/video, text).

Model Description

• Developed by: google
• Quantized by: llmware
• Model type: gemma-3
• Parameters: 4 billion
• Model Parent: google/gemma-3-4b-it
• Language(s) (NLP): English
• License: Gemma
• Uses: Multimodal LLM
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website