Google Launches Gemma 3, A Powerful Yet Lightweight Family of AI Models

Google has just launched the latest addition to the Gemma family of generative AI models, Gemma 3. It is a collection of lightweight, super-smart AI models based on Gemini 2.0. With a remarkable 100 million downloads within its first year and an impressive community that has crafted over 60,000 variants, Gemma has established itself as […]

Qwen2.5-VL, Qwen’s New Multimodal AI Model That Outperforms OpenAI GPT-4o

Alibaba Qwen team has launched Qwen2.5-VL, a series of multimodal AI models. These useful vision-language models are a huge upgrade to the predecessor, Qwen2-VL. It stands tall among its competitors, including Claude Sonnet and OpenAI’s GPT-4o, boasting open weights and versatile applications. The models can process and understand both visual and textual data. The models […]

SmolVLM 256M, The World’s Smallest AI Model, Running 100% Locally in-Browser on WebGPU

The research team at Hugging Face has developed SmolVLM 256M, the world’s smallest multimodal AI model. The model combines vision and language understanding to deliver powerful AI capabilities right at your fingertips. SmolVLM 256M is not only compact but also powerful, capable of running efficiently in-browser on WebGPU. Designed with efficiency and versatility in mind, […]

Learn How to Run Moondream 2b’s New Gaze Detection on Your Own Videos

Imagine being able to understand exactly where someone in a video is looking. It sounds like science fiction, right? Well, get ready, because with the power of Moondream 2b, this is now a reality you can explore yourself. Vision language models (VLMs) are changing the way computers “see” and understand the world, and Moondream 2b is a fantastic example of […]