Sep 3, 2026
Perplexity has launched Hybrid Compute, allowing users to combine cloud and local AI models while keeping sensitive data on their Mac, and open sourced Lily, a Rust + Metal inference engine for running Qwen3.6-35B-A3B on Apple Silicon that powers the local processing capability.
Liquid AI open-sourced Pipette, a benchmarking suite for on-device AI models, while Perplexity launched Portable Computer for local AI processing. The releases reflect a broader industry shift toward running AI models directly on user hardware rather than cloud servers.
Perplexity has released Portable Computer, a local-first AI agent platform that runs entirely on Nvidia DGX Spark hardware with zero per-token costs for local operations, only accessing the cloud when explicitly needed.
Meta Platforms has released Muse Glimmer, a 30-billion-parameter AI model from its Superintelligence Labs that can run locally on consumer laptops and GPUs. The model is being distributed as open-weight software under an Apache 2.0 license, reigniting debate over whether powerful AI technology should be freely available.
Ukraine-based app developer MacPaw has announced a strategic partnership with Liquid AI to develop on-device AI technology for macOS, starting with its Eney assistant and eventually making the stack available to developers building apps for its Setapp platform.
Google has launched Gemma 4 12B, an open-source AI model that can analyze audio and video while running entirely on enterprise laptops with 16GB of RAM, marking a focus on smaller, locally-deployable models rather than larger cloud-based alternatives.