Virtualization Review

Google Pushes AI Inference Out of the Cloud and Into the Browser

LiteRT.js runs machine learning models locally with CPU, GPU and emerging NPU acceleration, potentially reducing server infrastructure, inference charges and data movement.

Thinking Machines open sources first multimodal language model, Inkling, focused on low cost and 'resistance to censorship'

An Apache 2.0 designation makes Inkling a true open-source foundation. This gives developers the legal freedom to download, ...
XDA Developers on MSN

I'm running a 284-billion-parameter model locally, and it competes with cloud AI

DeepSeek V4 Flash can be run locally thanks to some wizardry, and it works really well.