A 27B AI Model Now Fits an iPhone - Apple Is Watching
PrismML compressed a 27B-parameter Qwen model from 54GB to under 4GB using 1-bit and ternary weights, and Apple is evaluating the technology for on-device Siri.
Articles Tagged "Edge AI"
Bonsai 27B
Bonsai 27B compresses Alibaba's Qwen3.6-27B into 1-bit and ternary weights, shrinking a 54GB model to as little as 3.9GB so it runs on an iPhone.
Ministral 3 8B
Mistral AI's mid-tier open-weight edge model - 8B parameters, 256K context, Apache 2.0 license, built for agentic pipelines and cost-sensitive production workloads.
Google Gemma 4 QAT Fits Frontier AI in Under 1GB
Google DeepMind's new QAT checkpoints shrink the Gemma 4 E2B model to under 1GB, making serious on-device AI viable for phones and budget laptops.
NVIDIA Cosmos 3
NVIDIA Cosmos 3 is an open physical AI omnimodel with Mixture-of-Transformers architecture that natively handles text, images, video, sound, and robot actions in a single 16B or 64B model.
Ministral 3B
Mistral AI's smallest open-weight model - 3B parameters, 256K context, Apache 2.0 license, built for edge and cost-sensitive deployments.
LetinAR Scores $18M for the Optics Behind AI Glasses
South Korean startup LetinAR raises $18.5M to scale its PinTILT optical modules, which already power AI glasses and AR helmets as shipments hit 8.7 million units globally in 2025.
Chrome Installs 4 GB Gemini Nano Without Asking
Google Chrome silently installs a 4 GB Gemini Nano model file on user devices with no consent prompt and re-downloads it if you delete it.
Apple's Next CEO Is the Engineer Who Built Its Chips
Tim Cook becomes executive chairman and John Ternus, the hardware engineer behind Apple Silicon, takes the CEO role on September 1 - a clear bet that chips beat software in the AI race.
Edge and Mobile LLM Leaderboard 2026: Phi, Gemma, Qwen
Rankings of the best LLMs for on-device edge inference - phones, laptops without GPUs, Raspberry Pi, and Jetson - scored by quality benchmarks and real tokens/sec on iPhone, MacBook, and Raspberry Pi 5.
Google AI Edge Gallery Puts Gemma 4 on Your Phone
Google's AI Edge Gallery officially launched on the Play Store and App Store on April 9, running Gemma 4 E2B and E4B models fully offline on any phone from Android 12 or iOS 17 onward.
Google Gemma 4 Ships Four Open Models Under Apache 2.0
Google releases Gemma 4 with a 26B MoE, 31B Dense, and two edge variants under Apache 2.0 - claiming the highest intelligence-per-parameter of any open model.
