Would be awesome if it ran Qwen (the MoE probably won't squeeze that low, but...). This because I have hardly been able to use Gemma for any sort of useful coding.
Gemma 4's tool calling was recently fixed; that was the main issue with agentic use in my experience. Otherwise IMO it codes about as well as the Qwen MoE for PHP and SQL. It's a fully impressive model (though it is not as mindbendingly impressive as the 12B, which is outrageously good for its footprint)
Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
381–382 of 382 posts
Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
#382Earlier quoted context omitted.
Asahi is a very cool project, and worthwhile if someone goes into it well aware of the major tradeoffs they're making, including reduced hardware functionality and support, which is improving, and significantly degraded security, which will likely always be the case. macOS is the only OS which fully supports M1 hardware and its security features. Please see Asahi Linux's documentation: https://asahilinux.org/docs/pla…
> and worthwhile if someone goes into it well aware of the major tradeoffs they're making Are you suggesting me to write all tradeoffs of everything that I suggest?
"So install Asahi Linux?" lacks substance. While I'm sure some four-word responses can contain a great deal of substance, this one didn't. Stating even a single tradeoff or implication of your suggestion would have been one way to have contributed something of substance. There are other ways, of course. You reached for none of them in that comment.
A substantive comment really shouldn't resemble something which could be achieved via a small set of macros.
Shallow promotion also runs the very real risk of turning people off of what you're promoting, and I actually agree with you on the value of some of your favorite software projects (even if our reasons may not fully align). In both positive and negative forms, a shallow one-liner may cause others to take the few seconds you didn't to add basic context which could prevent casual observers from being potentially misled or misinformed, or from taking a needlessly dim view of something due to consistently deficient messaging.