Nativ: Run frontier open models locally on your Mac

Post by IshKebab » Tue, Jul 21, 2026, 6:29 AM UTC

andsoitis wrote: post #82

chrisweekly wrote: post #56

Earlier quoted context omitted.

true but tfa's title says "frontier open models"

> tfa's title says "frontier open models" Does it? I read: "Run AI models locally on your Mac."

Post by jsomedon » Tue, Jul 21, 2026, 7:00 AM UTC

Post by flyingcapabara » Tue, Jul 21, 2026, 7:53 AM UTC

Post by a3w » Tue, Jul 21, 2026, 8:16 AM UTC

moostii wrote: post #51

D13Fd wrote: post #16

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.

LM studio is closed source software built ON TOP OF code released by the author of Nativ.

Post by regexorcist » Tue, Jul 21, 2026, 9:29 AM UTC

shitcoder wrote: post #53

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