Most active commenters
  • seanmcdirmid(3)

←back to thread

MCP in LM Studio

(lmstudio.ai)
227 points yags | 11 comments | 25 Jun 25 17:27 UTC | HN request time: 0.243s | source | bottom
Show context
chisleu ◴[25 Jun 25 17:58 UTC] No.44380098[source]▶
Just ordered a $12k mac studio w/ 512GB of integrated RAM.

Can't wait for it to arrive and crank up LM Studio. It's literally the first install. I'm going to download it with safari.

LM Studio is newish, and it's not a perfect interface yet, but it's fantastic at what it does which is bring local LLMs to the masses w/o them having to know much.

There is another project that people should be aware of: https://github.com/exo-explore/exo

Exo is this radically cool tool that automatically clusters all hosts on your network running Exo and uses their combined GPUs for increased throughput.

Like HPC environments, you are going to need ultra fast interconnects, but it's just IP based.

replies(14): >>44380196 #>>44380217 #>>44380386 #>>44380596 #>>44380626 #>>44380956 #>>44381072 #>>44381075 #>>44381174 #>>44381177 #>>44381267 #>>44385069 #>>44386056 #>>44387384 #
1. imranq ◴[25 Jun 25 19:35 UTC] No.44381075[source]▶
I'd love to host my own LLMs but I keep getting held back from the quality and affordability of Cloud LLMs. Why go local unless there's private data involved?
replies(3): >>44383336 #>>44385249 #>>44388345 #
2. mycall ◴[26 Jun 25 01:11 UTC] No.44383336[source]▶
Offline is another use case.
replies(1): >>44383597 #
3. seanmcdirmid ◴[26 Jun 25 02:03 UTC] No.44383597[source]▶
Nothing like playing around with LLMs on an airplane without an internet connection.
replies(2): >>44383945 #>>44388368 #
4. asteroidburger ◴[26 Jun 25 03:30 UTC] No.44383945{3}[source]▶
If I can afford a seat above economy with room to actually, comfortably work on a laptop, I can afford the couple bucks for wifi for the flight.
replies(2): >>44384251 #>>44388091 #
5. seanmcdirmid ◴[26 Jun 25 04:44 UTC] No.44384251{4}[source]▶
If you are assuming that your Hainan airlines flight has wifi that isn't behind the GFW, even outside of cattle class, I have some news for you...
replies(1): >>44384457 #
6. sach1 ◴[26 Jun 25 05:33 UTC] No.44384457{5}[source]▶
Getting around the GFW is trivially easy.
replies(1): >>44389173 #
7. PeterStuer ◴[26 Jun 25 08:06 UTC] No.44385249[source]▶
Same. For 'sovereignty ' reasons I eventually will move to local processing, but for now in development/prototyping the gap with hosted LLM's seems too wide.
8. MangoToupe ◴[26 Jun 25 14:58 UTC] No.44388091{4}[source]▶
Woah there Mr Money, slow down with these assumptions. A computer is worth the investment. But paying a cent extra to airlines? Unacceptable.
9. diggan ◴[26 Jun 25 15:27 UTC] No.44388345[source]▶
There are some use cases I use LLMs for where I don't care a lot about the data being private (although that's a plus) but I don't want to pay XXX€ for classifying some data and I particularly don't want to worry about having to pay that again if I want to redo it with some changes.

Using local LLMs for this I don't worry about the price at all, I can leave it doing three tries per "task" without tripling the cost if I wanted to.

It's true that there is an upfront cost but way easier to get over that hump than on-demand/per-token costs, at least for me.

10. diggan ◴[26 Jun 25 15:29 UTC] No.44388368{3}[source]▶
Some of us don't have the most reliable ISPs or even network infrastructure, and I say that as someone who lives in Spain :) I live outside a huge metropolitan area and Vodafone fiber went down twice this year, not even counting the time the country's electricity grid was down for like 24 hours.
11. seanmcdirmid ◴[26 Jun 25 16:59 UTC] No.44389173{6}[source]▶
ya ya, just buy a VPN, pay the yearly subscription, and then have them disappear the week after you paid. Super trivially frustrating.