25 articles tagged with “edge-ai”.
Nvidia's RTX Spark N1X, an Arm-based laptop SoC with RTX Blackwell graphics and large unified memory for running local AI models, ships in Windows laptops from six manufacturers.
Meta has released Muse Spark Open, an open-weight AI model built in collaboration with Apple to run locally on Apple silicon.
NVIDIA released Nemotron 3.5 Super VL, an open 120-billion-parameter model, alongside two new Nemotron 3.5 Bolt edge models aimed at local agentic workloads.
Amazon's Bee wearables, which listen to daily conversations to produce summaries and to-dos, are gaining a shopping capability, with two devices priced at $74.99 and $99.99.
Bee, owned by Amazon, released its first new AI devices since acquisition: an updated wearable and a card-sized recorder, starting at $74.99.
Google DeepMind and GovTech Singapore are building a fine-tuned, lightweight on-device Gemma model to intercept conversational scams in private chats with no cloud data egress.
Cerebras CEO Andrew Feldman forecasts a future where personal AI assistants are as common as household appliances, operating partly on local devices and partly in the cloud.
NVIDIA introduces RTX Spark, a superchip-based PC platform offering up to 128GB of unified memory and 1 petaflop of AI compute, with a ready global PC app ecosystem.
A Verge author documents their first attempts at running AI models locally rather than in the cloud, exploring privacy concerns, hardware demands, and whether the effort is worthwhile.
Google launched Google AI Edge Foresight, a free experimental macOS app that transcribes and summarizes meetings offline using its on-device EmbeddingGemma 2 model.
Microsoft disclosed the specs and price of its Surface Laptop Ultra, AI PCs running on Nvidia chips and designed to run AI models and agents.
Microsoft's Surface RTX Spark Dev Box is up for preorder at roughly $6,000, shipping in November, powered by Nvidia's Arm-based RTX Spark platform with 128GB of unified memory.
Music startup Thoughtful Things has launched a Kickstarter for Engram, a sampler and groovebox that runs a local, custom-trained AI model to distort audio and hallucinate new experimental sounds.
Meta highlighted its growing line of smart glasses at its Connect event, positioning the wearables as a way to keep consumers connected to the digital world.
Meta announced it is working on bringing its Muse agent to smart glasses, allowing voice activation for tasks such as guiding workouts, logging meals, and shopping.
SimpliSafe launched the Video Doorbell Series 2 with 2K resolution and dual-band Wi-Fi, combining AI threat detection with live agents who can intervene remotely.
Microsoft has named its developer-focused Windows experience Project Zenith, built for new devices with 64GB or more of unified memory and preconfigured for local AI model work.
NVIDIA's GeForce NOW releases its native Linux app out of beta, adds cloud optimizations for Frame Generation, and raises frame rates for Performance members.
A Hugging Face Blog post introduces LFM2.5-2.6B, presented as a way to deploy local AI agents across environments.
Friend has relaunched its AI pendant, adding a speaker so the device can talk aloud rather than only messaging back, now sold at double the previous price.
Halliday's second-generation smart glasses replace the criticized movable display window from the original with a more conventional design that a reviewer found improved.
NVIDIA unveiled the T3000 and T2000 modules based on its Thor architecture, aimed at bringing compact, power-efficient AI computing to mass-market robotics and edge AI.
Apple's shelved self-driving car project drove the creation of the Neural Engine, the on-device AI processor first shipped in the iPhone X and A11 Bionic.
The race is no longer only about bigger models. Small language models that run cheaply — even on a phone — are one of AI's most important trends. Here is why, and what to watch.
Ollama turned 'running an LLM locally' from a weekend project into a single command. Here is what it does well, where it hits limits, and when local models beat cloud APIs.