Name: ModelNap
Rating: 5.0 (2 reviews)

Free, open source menu bar app that turns Ollama and Splash on and off in one click and unloads idle models from memory. It stops Ollama the way it started (Ollama.app, brew services or ollama serve). No accounts, no telemetry. macOS 14+.

Hi Product Hunt! 👋 I'm Erik. I run local models with Ollama on my Mac, and a loaded model can hold 15–20 GB of memory long after I've stopped using it. Killing the process didn't always work either: with brew services, a LaunchAgent brings it right back. So I built ModelNap, a tiny native menu bar app: • One click (or ⌥⌘O) turns Ollama on or off, using the same mechanism it started with • Idle models are unloaded after 5–60 minutes; Ollama stays on and reloads them on the next message • New in 1.3: it also controls Splash (Inco AI), shows its real memory, and makes room by unloading Ollama first • No accounts, no telemetry, nothing sent to the internet. MIT licensed. It's free and open source. llama.cpp support is next on the list, so tell me how you run your local models!

Love the idea behind ModelNap, especially how simple it makes managing local models without adding more complexity.

Also, Erik is one of those founders who’s genuinely involved with his community, always answering questions, sharing knowledge, and helping others.

Congrats on the launch, Erik! 👏

Hi @eriktaveras , it is awesome. Huge Thanks for this contribution. I have started to learn and use some local AI for some personal automatizations and some for my business

ModelNap solves a simple but very real problem when running local AI models on a Mac. It makes it easy to control Ollama directly from the menu bar and automatically unload idle models to free up memory. I especially like that I don’t have to keep opening Terminal just to stop services or manage models manually. It’s lightweight, straightforward, open source, and has no telemetry.

I’d like to see even more visibility into resource usage, such as RAM being used by each loaded model and how much memory was freed after unloading it. More granular automation settings per model would also be useful as the app evolves.

I was mainly managing Ollama manually through Terminal and checking memory usage myself. ModelNap is much more convenient because it puts those controls in one place and handles idle models automatically. I prefer having a small dedicated utility instead of adding more manual commands to my workflow.

Love the idea behind ModelNap, especially how simple it makes managing local models without adding more complexity.

Also, Erik is one of those founders who’s genuinely involved with his community, always answering questions, sharing knowledge, and helping others.

Congrats on the launch, Erik! 👏

Hi @eriktaveras , it is awesome. Huge Thanks for this contribution. I have started to learn and use some local AI for some personal automatizations and some for my business

ModelNap

Your local AI, on only when you use it

Your local AI, on only when you use it

What's great

What needs improvement

vs Alternatives

What's great

What needs improvement

vs Alternatives