Nativ: Run frontier open models locally on your Mac

Post by andsoitis » Tue, Jul 21, 2026, 2:45 AM UTC

oersted wrote: post #72

moontear wrote: post #7

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 was confused too, but I believe that it refers to the Pareto Frontier: the best set of solutions to a multi-objective problem. Look it up, it’s a bit difficult to explain concisely in words but it is intuitive visually. If we are thinking of intelligence and price, a model will be in the Pareto Frontier if there’s no cheaper model of the same or higher intelligence. Or if there’s no more intelligent model for that…

Post by netghost » Tue, Jul 21, 2026, 2:50 AM UTC

JosNun wrote: post #47

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?

Post by justatdotin » Tue, Jul 21, 2026, 3:11 AM UTC

simonw wrote: post #77

erikkahler wrote: post #35

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 mod…

I was so excited when I saw "blaizzy" in the domain, because Prince Canuma's work around MLX has been of such uniquely high quality.

Post by jdthedisciple » Tue, Jul 21, 2026, 5:26 AM UTC

moontear wrote: post #7

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?

Post by febed » Tue, Jul 21, 2026, 6:19 AM UTC

mips_avatar wrote: post #63

JosNun wrote: post #47

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?

Qwen35ba3b can do a huge amount of data cleaning work on pretty modest hardware. Already have run about 100 billion tokens on it using 2x3090 gpus.