Tag
10 articles
Nvidia launches new open models to enable enterprises to run custom AI agents in their own data centers and on local PCs, responding to growing demand for private, on-premises AI solutions.
Google's EmbeddingGemma 2 outperforms rival models twice its size, offering a lightweight solution for on-device AI applications.
Learn how to work with vision-language models using Python and Hugging Face Transformers, simulating core capabilities like screen reading, object grounding, and function calling.
Learn how Liquid AI's new on-device agentic model LFM2.5-2.6B can plan, use tools, and complete tasks locally on your device — all while keeping your data private.
PrismML has compressed a 27-billion-parameter AI model to under 4 GB, enabling it to run on an iPhone. Apple is reportedly testing the technology, which could advance on-device AI capabilities.
Learn how Qualcomm AI Hub Models helps run AI models directly on smartphones, making apps faster, smarter, and more private.
Perplexity AI introduces a hybrid local-server inference orchestrator that automatically routes AI tasks between on-device and cloud models, enhancing both performance and privacy.
Stanford researchers have released OpenJarvis, an open-source framework for on-device personal AI agents that offers cloud-level performance at a fraction of the cost.
Stability AI releases Stability Audio 3.0, a new audio model that can create six-minute songs and run on-device for extended musical compositions.
This article explains Alibaba's Qwen 3.5 Small Model Series, a new approach to AI model design that emphasizes efficiency and on-device deployment over traditional large-scale parameter increases.
