Liquid AI launches Pipette, an on-device LLM benchmark with live leaderboard
JosephJacks_ · x · 2026-11-02
Liquid AI released Pipette, an on-device benchmark answering which model runs best on your specific device — since it depends on the hardware, you have to measure. It includes a live leaderboard, and Claude generated a promo video from it in 20 minutes.
More from Infra
- There is no liquid 'GPU spot market': cloud preemptible pricing differs wildly across AWS, GCP, Azure, Nebius — josh_wills · 2026-11-03
- mlx-learn brings GPU-accelerated classical ML to Apple silicon with scikit-learn API — RichmanRonald · 2026-11-03
- llama.cpp PR Fixes Unified KV Cache for Multi-Seq, Speeding Up Local Agents — jacek2023 · 2026-11-03
- Pinokio ships "Remote AI" update for controlling local AI from anywhere — cocktailpeanut · 2026-11-03
- Pinokio Update Brings "Remote AI": Control Local AI Apps From Anywhere — cocktailpeanut · 2026-11-03
- Starcloud-1 marks one year in orbit with the only NVIDIA H100 in space, 3 more launches planned — ycombinator · 2026-11-03