Liquid AI Launches Pipette, an Open-Source Platform Benchmarking AI Models Across 1,000+ Edge Device Configurations
Summary
Liquid AI and Artificial Analysis launch Pipette, an open-source benchmarking platform testing 30+ AI models across 1,000+ edge device configurations, delivering real-world performance data on devices like the iPhone 17 Pro and MacBook Pro M5 Max through native apps and an interactive public dashboard.
Key Points
- Liquid AI, in partnership with Artificial Analysis, launches Pipette, an open-source benchmarking platform that measures how foundation models actually perform on edge devices across more than 1,000 model, quantization, runtime, and device configurations.
- Pipette releases a public dataset of lab-verified results, native benchmark apps for iOS, Android, macOS, and Windows, and an interactive dashboard that pairs quality evaluations with real-world throughput, latency, memory, and context scaling metrics.
- The platform currently covers 30+ models on devices including MacBook Pro M5 Max, iPhone 17 Pro, and Galaxy S26 Ultra, with AMD Ryzen AI Max+ results coming soon, while NPU support and cross-device comparisons remain active areas of development.