ModelHub is a native macOS menu bar app for developers working with local LLMs. It helps you discover models from Hugging Face, download the right local build, manage your model library, and use Hugging Face models with Ollama, MLX, LM Studio, llama.cpp, and the tools you already have without bouncing between browser tabs, terminal commands, model cards, and local folders. Ollama, MLX, and LM Studio are great tools. ModelHub is the missing discovery and management layer around them.
Hey Product Hunt 👋
We built ModelHub because local AI on Mac is getting good fast but the
workflow around models still feels scattered.
Ollama makes running local models simple. MLX makes Apple Silicon a stronger platform for inference. LM Studio gives people a great local model workspace. Hugging Face has the model ecosystem.
But as developers, we kept running into the same problem:
Finding the right model, checking the right format, downloading it, remembering what was installed, switching between Ollama, MLX, LM Studio, Hugging Face, and local folders, and keeping everything organized still involved too many tabs, terminal commands, and disconnected tools.
So we built ModelHub: a native macOS menu bar app for discovering, downloading, and managing local LLMs from Hugging Face, then using them with Ollama, MLX, LM Studio, llama.cpp, and the tools you already use.
It is not trying to replace Ollama, MLX, LM Studio, or llama.cpp.
It is meant to sit beside them.
Think of it as the missing model manager for your local AI setup.
We’d love feedback from:
- Developers running models locally on Mac
- Ollama users
- LM Studio users
- MLX / Apple Silicon builders
- People testing coding models locally
- Anyone who has too many model files sitting in random folders
Specific feedback we’re looking for:
1. What model metadata matters most before downloading?
2. Should we prioritize Ollama, MLX, LM Studio, or all workflows equally?
3. What would make this useful enough to keep in your menu bar app every day?
Thanks for checking it out. We’ll be in the comments all day.
I dont see Ollama as source in the local tab. Does it require additonal work to see my local ollama models?
This feels like the right layer to exist around local LLM tooling. The hard part with local models is more than“can I run it?” It's knowing which build fits the machine, what licence applies, where it was downloaded, whether it duplicates something already installed, and what worked for a previous task. I’d be especially interested in metadata around commercial use, context length, RAM estimate, quantisation, and notes per model/use case.
Hey Priyanshu, was poking around ModelHub's page and the "workflow around models still feels scattered" line nailed something I've been quietly annoyed by. one thing I wanted to ask, when you sit on top of Ollama, MLX, and LM Studio together, are you reading their model configs in place or maintaining a unified registry that gets synced? where the source of truth lives is the part I'd want to understand.
I'm rather happy to do this semi-manually (finding the model on huggingface and copy-pasting the llama.cpp command to run it), but this is a great idea!
this is a very practical tool , keeping local models organized is a real pain.
I've been bouncing between Hugging Face tabs and Ollama CLI way too often. Having a single menu bar app that handles discovery + download + management sounds like exactly the missing layer. Curious if it supports quantized model filtering (like GGUF Q4 vs Q8) — that's usually the first thing I check before pulling a model locally.
Local LLMs via menu bar is the right UX switching between models shouldn't require a browser tab. Does it handle model downloads itself or do you bring your own? Curious about the memory footprint running models in the background.
I usually encounter more issues with how to quickly validate whether a model is suitable for your scenario after obtaining it, and whether there is corresponding code that can quickly verify and reduce the time spent trying one by one. I would like to know if your tool has such a function or scenario.
Does ModelHub also track which models are actually being used so you can archive the ones you never run?
Does ModelHub handle quantization format filtering during discovery — like surfacing only Q4_K_M builds based on available VRAM, or is model selection still manual?
I like that this isn’t trying to become another LM Studio or Ollama replacement. Simpler UI to just manage my local LLMs.
Was that an intentional product call from day one? Also, do you see this becoming more recommendation-driven, like “best models for your Mac” based on chip/memory?
Quick one on storage - if I've already pulled Qwen 32B via Ollama and then discover it again in ModelHub, do you dedupe against the existing local file? Or do I end up with two copies eating 20GB? Well done guys overall
Hey folks! We built modelhub to manage your cluttered local models! Do check it out and give us valuable feedback! :D
Congrats on the launch! 🚀 Having one unified menu bar app to manage models across Ollama, LM Studio, and MLX makes organizing and discovering Hugging Face models way cleaner.
The "Runs on this Mac" hardware checker sounds incredibly useful before committing to a massive download. Can't wait to give this a spin!
The 'Runs on this Mac' feature for checking if a model can run on the hardware that I have is my favourite part! That's usually the first thing I want to know before downloading some huge model.
Two things I'd love to see: more pre-download details like license, context length, and RAM estimate, and a quick way to open the original Hugging Face model card from inside the app.
Congrats on the launch! Having one place to manage across Ollama, MLX, and llama.cpp is something I've been doing by hand for too long. Gonna give this a try.
I have lmstudio already and Unsloth and would like to share models across.
What does this do then? Does this solve for what I am looking for?
About ModelHub on Product Hunt
“The missing menu bar app for local LLMs on Mac.”
ModelHub launched on Product Hunt on May 24th, 2026 and earned 307 upvotes and 41 comments, earning #2 Product of the Day. ModelHub is a native macOS menu bar app for developers working with local LLMs. It helps you discover models from Hugging Face, download the right local build, manage your model library, and use Hugging Face models with Ollama, MLX, LM Studio, llama.cpp, and the tools you already have without bouncing between browser tabs, terminal commands, model cards, and local folders. Ollama, MLX, and LM Studio are great tools. ModelHub is the missing discovery and management layer around them.
ModelHub was featured in Open Source (68.4k followers), Developer Tools (513.3k followers), GitHub (41.2k followers) and Menu Bar Apps (12.2k followers) on Product Hunt. Together, these topics include over 107k products, making this a competitive space to launch in.
Who hunted ModelHub?
ModelHub was hunted by Priyanshu Ratnakar. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how ModelHub stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Priyanshu Ratnakar