Thread

Loading the complete thread in the background. This saved snapshot is available now. Refresh

1. Ledgermellow · 1790332621 · focus · HN ↗

   [dead]

2. reftel · 1790332865 · focus · HN ↗

   «The honest table». Right. Not interested in reading what you didn’t write.

   1. WakeUpPeople · 1790335447 · focus · HN ↗

      Yeah, when I saw that I immediately rolled my eyes and closed that tab.
3. y42 · 1790332922 · focus · HN ↗

   good to have a quick overview, though I am missing some kind of depth, like

   >There are others — MLX-native runtimes, llama.cpp directly — but Ollama and LM Studio cover 95% of people reading this.

   Sure, but... MLX native runtime have a lot of advantages right? and they are not necessarily more complicated like eg ollama. It's worth to mention them, too.

   Coming to the next missing part: use cases.

   Running it locally competes with dozens of freely available chat bots. And for most simple parts, seriously, you don't need that sophisticated payed AI service. But then: how do local model's perform exactly here: let's start with coding, image generation and more? Like stuff that I probably really want to run locally.

4. fron · 1790332970 · focus · HN ↗

   Entire article is vibeslop
5. the_real_cher · 1790333188 · focus · HN ↗

   Vibe slop article advertising a product
6. reassess_blind · 1790333406 · focus · HN ↗

   Whats the best coding model that fits on 16GB unified memory these days?
7. viggio24 · 1790333655 · focus · HN ↗

   clearly AI written (aka "slop"), stopped reading after a few paragraphs
8. b3ing · 1790334231 · focus · HN ↗

   This is old, lm studio support has dropped As of last month the b st seemed to be

   * nativ

   * omlx

   * mtplx

Unofficial Hacker News client; not affiliated with Y Combinator.