Search results for Ollama
AI & Enterprise
Google unveils Gemma 4 QAT for mobiles and laptops to cut AI memory use sharply
Google unveiled Gemma 4 QAT, a version of its Gemma 4 model family designed to sharply reduce memory use so large AI models can run more easily on smartphones and standard laptops. It applies quantization-aware training, simulating quantization during training to limit quality loss. Google said the approach can preserve response quality while lowering memory needs. The models are free under the Apache License 2.0 and officially support local runtimes such as llama.cpp, Ollama and LM Studio.
AI & Enterprise
Personalisation that general-purpose AI cannot do can be solved with local AI, founder says
Weeklay founder Yoon Joo-hyun (윤주현) said his company is betting on local AI to deliver personalisation that cloud-based general-purpose AI lacks. Weeklay’s local AI agent platform, Aulo, runs entirely on a PC without connecting to cloud servers, keeping personal data on-device. Users download Aulo and train it on their own data, then can share trained agents through an outlet feature while keeping underlying training data hidden.
AI & Enterprise
Google unveils open model Gemma 4, supports complex reasoning on low-power devices
Google has unveiled its open-weight AI model family Gemma 4, SiliconANGLE reported on Wednesday. The company said Gemma 4 is based on the same architecture as Gemini 3 and can run complex reasoning and autonomous AI agents locally on low-power devices such as workstations and smartphones. The lineup includes E2B, E4B, a 26B Mixture of Experts model and a 31B dense model. It supports tool integration and multimodal inputs.