Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

Post by jackbravo » Tue, Aug 11, 2026, 5:59 AM UTC

dofm wrote: post #272

mmaunder wrote: post #249

Remember when we needed 200 servers for an enterprise website because Apache used one process or thread per connection - and Nginx collapsed that into a single box overnight? That moment for LLMs is near. It’s going to move us from the big iron era of AI to small portable brains. Nature has already proved it’s possible with 20 watts and very little heat generation. And I think the data center buildout will end in car…

Side note! Nginx was by no means the first web server to use a non-forking mechanism, nor the first open source web server to do so. Certainly Zeus (which was closed source) was earlier and very useful in this sort of application, and so was thttpd (open source, still exists as Merecat). I used thttpd quite a bit for single box applications and at one of my employers, nginx replaced a mixed strategy with Zeus, Apache…

Post by TokenLat » Tue, Aug 11, 2026, 6:20 AM UTC

Post by Koffiepoeder » Tue, Aug 11, 2026, 6:42 AM UTC

Arwill wrote: post #459

modzu wrote: post #294

Earlier quoted context omitted.

brains do it with 20 watts because theyre analog. llms require massive amounts of power and this isnt changing any time soon without a breakthrough

There are arguments that the brain is quantum, as in parts of it locally using quantum effects. Which if true, might make a counter-argument, as there will be bigger data centers needed if the goal is to simulate the brain classically. On the other side, advancement in quantum computers would make current LLM inference much faster. Because of the extreme cooling needed, i dont think the energy demand would become les…

Post by lukaslalinsky » Tue, Aug 11, 2026, 6:48 AM UTC

arkmm wrote: post #571

Computer0 wrote: post #546

Earlier quoted context omitted.

If you are willing and not too busy, What model do you use and what is your cost? (If using subscription would you be able to check with 'npx ccusage').

I'd also be really curious about the cost to run something like this, and what things you think it's particularly helpful for?

Post by dofm » Tue, Aug 11, 2026, 7:02 AM UTC

keeda wrote: post #624

dofm wrote: post #585

Earlier quoted context omitted.

> So far everyone seems to be consistently GPU-poor, despite the huge buildout That is seemingly not the case. The buildout is actually slow; almost nothing of these giant projects has been completed. Nobody will say how much of anything they have actually finished. And Nvidia have made huge, huge buy-and-hold deals for GPUs that do not have data centres to go into. Everyone is GPU poor because stuff hasn't been fini…

If I understand correctly, you're saying people are compute-poor but not necessarily GPU-poor because there's a lot of GPUs out there but nowhere to plug them into? If so, I'm not sure that distinction matters to the GP's point that there is too much demand to call this an oversupply. I also doubt we can estimate the level of demand based on a single deal between Anthropic and SpaceX (despite which, note, Claude stil…