alt Hacker NewsNativ: Run frontier open models locally on your Mac
Comments
Is „frontier“ overused? I thought frontier models were the best-of-the-best such as Fable right now. I assume you can’t host these models yourself since you would need many GB of RAM and expensive GPU of is my thinking of „frontier models“ wrong?
I'm surprised that their home page basically acts as if LM Studio and others don't already do this. It's not clear what the difference is from a glance.
It also omits Open WebUI. I've been running Deepseek V4 Flash locally on my Macbook Pro for weeks using Open WebUI + DS4.
I can't really tell why would I use this over like lm studio, jan.ai and such?
Genuinely curious: what are people using these smaller local models for? They are getting decently capable, but they are still small enough that I don't trust them for "real" work outside of a handful of fun toy projects.
Are people actually using them in coding agents? Or are they mostly using them for other things?
Looking forward to giving this a try. I have tried MLX using Rapid MLX however the LLM (Qwen) would always have hiccups and get stuck repeating itself.
Moving onto llama.cpp I was able to get faster tokens with MTP and a more reliable llm.
I wonder what other people's experiences are using MLX vs llama.cpp
This looks like the Prism folks, who are making binary/ternary versions of popular edge models, so that those models will fit on constrained devices like phones. E.g., their Bonsai model derived from Qwen:
https://news.ycombinator.com/item?id=48910545
Perhaps they got tired of LM Studio, etc., not being able to run their models properly.
Only interesting thing about this vibe coded runner is the MLX support, as that's still annoying to use in other ones, most still use GGUFs. Unsloth Studio which is an OSS runner I use is still in progress with MLX support although it's still a ways away.
Ironic that the app is named Nativ(e) and yet bundles a full Python runtime. Nonetheless, still less bloated than LM Studio, which bundles a full Python runtime and electron.js (which in turn bundles a whole browser runtime).
The server wont start for me. "ERROR: Application startup failed. Exiting." "mlx-vlm-server stopped with status 3"
Is Gemma 4 E2B actually "usable"? I've been running Gemma 4 12B and it handles everything very well! But the second I've moved down to E4B it's been unable to perform the simplest of tasks. So I can't even imagine how E2B would do... Or am I doing something wrong?
I'm a bit curious why not running DeepSeek V4 on top of https://github.com/antirez/ds4. I think the results could be really good.
Has anyone found a model that can run on a normal macbook? I have an M3 Pro with 18GB of memory and whenever I try to run even a basic model the fans goes off and the mac starts to get heated up and becomes so laggy.
Advice: remove all slop and fluff from the website such as "Everything you need. Nothing you don’t."
Just state the information you want to communicate in the plainest and most straightforward way possible.
so now we have this, https://pypi.org/project/rapid-mlx/, https://mtplx.com, and the oldest I could find at https://omlx.ai.
Ok, so we're at the point that even design are just one-shot by AI. This is exact look and feel any time I ask it to present a HTML doc about anything.
Looks like my call [0] for more competitors to Ollama has been answered.
We need more like this as well as llama.app, which also has a native mac app.
[flagged]
[flagged]
[flagged]
[dead]
To clarify, this MIT-licensed app is from the very same dev, 'Prince Canuma', who maintains the popular MLX-VLM library (https://github.com/Blaizzy/mlx-vlm). MLX-VLM is a long-time dependency of the excellent LM Studio and others because it can provide faster inference on Apple devices than llama.cpp. Historically, MLX is a smaller community than CUDA, but has some of the fastest updates upon the release of new models, particularly in models with modalities beyond text-in, text-out (vision, STT, TTS, video gen). See also (https://github.com/Blaizzy/mlx-audio-swift). Would be totally unsurprised if those modalities and models get integrated into this UI.
Possibly vibe-coded landing page notwithstanding, the app is mostly written in Swift language. That suggests it will be easy to port this inference stack to iPad and iPhone.