Liquid AI releases Pipette, an open-source benchmark for on-device AI models
JosephJacks_ · x · 2026-08-25
Liquid AI, in partnership with Artificial Analysis, has released Pipette, an open-source evaluation suite designed specifically for measuring AI model performance on edge devices like phones, laptops, and AI boxes.
- On-device focus: Addresses the gap in existing cloud-centric benchmarks by providing a common way to measure quality, speed, latency, and memory usage locally.
- Comprehensive data: Includes a warehouse of 10,000+ verified results spanning 35 model classes, 7 quantization types, and runtimes like llama.cpp.
More from Infra
- Jensen Huang: Musk's AI buildout moved from K's to M's, now a CSP-tier NVIDIA customer — elonmusk · 2026-10-16
- EpochAI pegs GPT-6 training at up to 1.8e27 FLOP; scaling01 calls param estimates way too high — scaling01 · 2026-10-16
- Meta's Muse Spark Open scores 39 vs 48 for closed Spark 1.3 on AA Intelligence Index — EAccelerate_42 · 2026-10-16
- LLM spots useless 95GB-per-frame memcpy in ffmpeg dblur, cutting runtime from 2452ms to 49ms — IgorCarron · 2026-10-16
- DeepSeek-V4-Flash on 4x Radeon AI PRO R9700: the 'refused' 4-card config hits ~79 tok/s — brainchillzZ · 2026-10-16
- Tree packing lands in TRL's AsyncGRPO, cutting agentic RL training compute by over 26x — joecole · 2026-10-16