news Pipette

Pipette | On-Device Foundation Model Benchmarks

Pipette is Liquid AI’s on-device foundation model benchmarking platform, designed to help users compare the best models for real-world device performance. It focuses on key metrics such as speed, latency, memory usage, quality, quantization, runtime, and hardware compatibility. The site’s main goal is to answer the question: “What model runs best on device?” The platform offers a leaderboard and results pages where users can explore benchmark data by device and model. It also highlights charts showing per-model performance, how performance changes with context length, and the memory cost associated with higher throughput. According to the site, speed and memory are measured directly on-device, while model quality is evaluated on an H100 GPU. Pipette also invites community participation through a preview program. Users can help collect benchmark data using iOS and Android apps or GitHub-based benchmark clients, with community submission support planned for the future. The platform provides links to documentation, feedback, glossary, and related Liquid AI resources, including its foundation models. The benchmark results shown are generated with Pipette v1, and the methodology has been independently verified by Artificial Analysis. Overall, Pipette is positioned as a practical tool for comparing foundation models across performance dimensions that matter most for deployment on phones and other devices.

Build this article’s timeline

Extract dated events, key actors, and open questions using the same timeline analysis available in Signal.

Log in to build

Timeline generation is available to signed-in community members.

Five Ws 🤖 5 AI prefills · all filled
Who
Liquid AI, Pipette, and Liquid Foundation Models
🤖 AI prefill
What
Pipette is Liquid AI’s on-device foundation model benchmarking platform, designed to help users compare the best models for real-world device performance.
🤖 AI prefill
When
2026
🤖 AI prefill
Where
United States and H100
🤖 AI prefill
Why
Centers on on-device foundation model benchmarks, foundation models, and benchmark data
🤖 AI prefill

Login to answer and earn XP for each gap you fill.

On-Device Benchmarks benchmark, leaderboard, device, performance, accuracy Model Comparison Metrics models, performance, context length, quantization, runtime Data Collection Methods submission, coverage, on-device, H100, quality Product Navigation leaderboard, results, submissions, docs, feedback
on-device foundation model benchmarks100% foundation models97% benchmark data92% model performance90% speed, latency, memory, and quality89% quantization87% inference benchmarks85% throughput84% context length80% on-device AI79%
2
Manipulation Score: Low How much this article uses emotional framing vs. straight reporting
Loaded Language 125%
Absolutist 115%
Threat/Panic 025%
Us vs Them 015%
Engagement Bait 220%
Manipulation score look right?

Factual Claims (10)

low technology
Pipette is an on-device foundation model benchmarking platform by Liquid AI.
low technology
It compares foundation models on real devices across accuracy, throughput, latency, memory, quantization, runtime, and hardware.
low technology
The site provides a leaderboard, results, submissions, feedback, and documentation pages.
low technology
Benchmarking focuses on model performance on a selected device.
medium technology
Speed and memory are measured on-device, while quality is evaluated on an H100.
low technology
Users can run benchmarks on their own iOS and Android devices using apps or clients.
medium technology
Community submission support is planned to be added soon.
low technology
The benchmark results shown were generated with Pipette v1.
medium technology
The methodology has been independently verified by Artificial Analysis.
low other
The page is copyrighted © 2026 by Liquid AI, Inc.

Comments

Login to view and post comments.

🏠Portal 📰Links ❓Q&A 📅Events 💼Jobs