menu-bar app · macOS

the missing menu bar
for local LLMs.

discover, download, and manage models from Hugging Face — then run them with Ollama, MLX, LM Studio, llama.cpp, and the tools you already use.

Github

requires macOS 26+ · apple silicon · ~4 MB

view changelog→

local LLMs are powerful.
managing them is still a headache.

you have models in LM Studio, the Hugging Face cache, Ollama, and maybe a few random folders, scattered on your mac.

every time you want to find, download, run, or remove one, you end up switching between browser tabs or terminal commands.

ModelHub brings the model layer into one place.

—— plays well with ——

Ollama
LM Studio
llama.cpp
MLX
oMLX
Hugging Face
vLLM
Ollama
LM Studio
llama.cpp
MLX
oMLX
Hugging Face
vLLM
Ollama
LM Studio
llama.cpp
MLX
oMLX
Hugging Face
vLLM

for the developers

zero lock-in. cache compatible.

every download replicates the official huggingface cache layout — blobs, snapshots, refs, the lot. a model fetched through ModelHub is byte-identical to one fetched with huggingface-cli. drop into any pipeline. uninstall anytime. no migration.

~/.cache/huggingface/hub/
└─ models--meta-llama--Llama-3.2-3B
├─ blobs/
└─ a3f9c… [1.8 GB]
├─ snapshots/
└─ 8b0c…/ → ../blobs/a3f9c…
└─ refs/main
✓ reads & writes the standard layout.
✓ ollama, mlx-lm, transformers, llama.cpp.
✓ uninstall ModelHub — keep your models.

—— ready when you are ——

one menu bar.
every model.

v1.4.0 · macOS 26+ · apple silicon

01
open .dmg
drag ModelHub into Applications.
02
launch it
look for the dot in your menu bar.
03
that's it
browse/manage your LLMs.
ModelHub - The missing menu bar app for local LLMs on Mac. | Product Hunt