Maid

Fully offline

Android Ollama client + on-device fallback for small models. Cross-platform Flutter.

Editorial verdict: “Best cross-platform Android-friendly Ollama client. Falls back to on-device for tiny models.”

Mobile app

Free

MIT

★ 4.0 / 5

GitHub ★ 2,000

↗ GitHub

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported

ollamallama-cpp

§ OS / platform

androidioslinuxmacoswindows

§ Hardware + model hint

Minimum VRAM

2 GB

Recommended starter model

Llama 3.2 3B Q4 (on-device) or any (server)

→ Build the rest of the stack with /stack-builder → Pick a GPU for this app

What it is

Maid is a Flutter app that lets you chat against a remote Ollama server (LAN / VPN) OR run small models directly on the phone via llama.cpp embedded. Cross-platform: Android, iOS, Linux, Windows, macOS. The 'Ollama client AND tiny on-device model' combo.

✓ Strengths

+True cross-platform (Android included)
+On-device + remote-server modes
+Open-source MIT

△ Caveats

−Flutter UI doesn't feel as polished as Enchanted on iOS
−On-device mode only viable for tiny models

About the Mobile app category

iOS / Android app that talks to your local model server.

§ Other mobile app apps

Enchanted

Best mobile Ollama client. Native SwiftUI; works against your home Ollama server.

Where to go from here

Stack Builder →

Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.

Back to /apps →

The full directory — filter by category, runtime, OS, privacy posture, or VRAM.

Runtimes (/tools) →

What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.

Community benchmarks →

Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.