Comment by simonw
3 days ago
This story talks about MLX and Ollama but doesn't mention LM Studio - https://lmstudio.ai/
LM Studio can run both MLX and GGUF models but does so from an Ollama style (but more full-featured) macOS GUI. They also have a very actively maintained model catalog at https://lmstudio.ai/models
LMStudio is so much better than Ollama it's silly it's not more popular.
LMStudio is not open source though, ollama is
but people should use llama.cpp instead
I suspect Ollama is at least partly moving away open source as they look to raise capitol, when they released their replacement desktop app they did so as closed source. You're absolutely right that people should be using llama.cpp - not only is it truly open source but it's significantly faster, has better model support, many more features, better maintained and the development community is far more active.
3 replies →
> but people should use llama.cpp instead
MLX is a lot more performant than Ollama and llama.cpp on Apple Silicon, comparing both peak memory usage + tok/s output.
edit: LM Studio benefits from MLX optimizations when running MLX compatible models.
> LMStudio is not open source though, ollama is
and why should that affect usage? it's not like ollama users fork the repo before installing it.
1 reply →
Note that there's also "LlamaBarn" (macOS app): https://github.com/ggml-org/LlamaBarn
Ollama did not open source their GUI.
2 replies →
ik_llama is almost always faster when tuned. However, when untuned I've found them to be very similar in performance with varied results as to which will perform better.
But vLLM and Sglang tend to be faster than both of those.
Besides optimizations specific to running locally lands in lamma.cpp first.
Makes me think it's a sponsored post.
LMStudio? No, it's the easiest way to run am LLM locally that I've seen to the point where I've stopped looking at other alternatives.
It's cross-platform (Win/Mac/Linux), detects the most appropriate GPU in your system and tells you whether the model you want to download will run within it's RAM footprint.
It lets you set up a local server that you can access through API calls as if you were remotely connected to an online service.
FWIW, Ollama already does most of this:
- Cross-platform
- Sets up a local API server
The tradeoff is a somewhat higher learning curve, since you need to manually browse the model library and choose the model/quantization that best fit your workflow and hardware. OTOH, it's also open-source unlike LMStudio which is proprietary.
5 replies →
Lmstudio runs llama.cpp under the hood.
They also run the Apple MLX engine on macOS.
I think you should mention that LM Studio isn't open source.
I mean, what's the point of using local models if you can't trust the app itself?
You can always use something like Little Snitch to not allow it to dial home.
> I mean, what's the point of using local models if you can't trust the app itself?
and you think ollama doesn't do telemetry/etc. just because it's open source?
You're welcome to go through the source: https://github.com/ollama/ollama/
That's why i suggested using llama.cpp in my other comment.
Depends what people use them for, not every user of local models is doing so for privacy, some just don't like paying for online models.
Most LLM sites are now offering free plans, and they are usually better than what you can run locally, So I think people are running local models for privacy 99% of the time
ramalama.ai is worth mentioning too