- cross-posted to:
- programming@lemmy.ml
- cross-posted to:
- programming@lemmy.ml
Seems like he’s been pushed into using LLMs as a way to cope with the deluge of LLM-generated security reports.
Seems like he’s been pushed into using LLMs as a way to cope with the deluge of LLM-generated security reports.
I run Qwen 3.6 27B at home. For “free”. It is extremely useful.
My point being that I’m not going to be priced out of using it
What hardware that needs? My issue with running local models was that it’s too much of a resource hog to be able to do gamedev on the same machine, and any sensible model needs pretty expensive hardware to just get a server for it. Especially with current prices.
Geforce 3090 with 24TB should be able to run a “Q5 version” of it. Maybe get a second older computer, or maybe you can run two cards in one PC.
64GB unified memory. I run it (and a lot more) on a dgx spark, but a Mac mini would suffice also.
You could prob run 4-bit version on a RTX card with 32g. Maybe even 24g. Like a 5090 or 4090 or such.
So much info out there.
Mac Minis top out at 48GB and are 1.8k when configured like that. It’s going to be at least $2k to buy anything that has a hope of running it at a reasonable speed.
Running local isn’t free, but at least it’s just a single upfront payment.
The M4 Pro Mac Mini caps out at 64GB RAM. Whether or not Apple can sell you that SKU right now is a different question with the ongoing DRAM shortage.
That (64GB) doesn’t appear on the site at the moment.
Don’t worry, they want to replace your hardware with a “cloud based computing solution” as well.
When did that absurdity come back? I thought we killed the cloud computer nonsense a decade ago.
Well you aren’t a brain dead business man then.
…yet
qwen is garbage. it can’t even count the elements within an array of numbers.
to be clear though, it’s not just qwen. all code models are fucking trash.
Are you sure you were using the actual coding model? There are a number of them
Qwen coder 30B A3B
Eh try Kimi
Yep, while I don’t use them myself, I saw the output of the latest models at the beginning of May. While there are some “good” things in it, the vast majority of the output was unnecessary maintenance load or just wrong. And, while the person showing off the output claimed they couldn’t have written the code, I didn’t see anything particularly special.
On top of that, I don’t believe the output of Qwen (or any other coding model) can be distributed without violating a large number of copyrights, so it’s entirely inappropriate for FOSS projects.
Into the trash it goes
I have a perfect example for that. I asked Qwen to write a simple python socket app. one for server and one for client.
While I was reading through forum posts about python socket communication, I found a post from 8 years ago. same script. same variable names. same comments. word for word. line for line. the same exact script.
so much for AI “not stealing content”.
Your post here reads like AI funnily enough
you’re absolutely right. I’m just old though and this is how we talk.
I guess it’s like telling someone they seem to be coming down with a cold, they probably already know
it’s a particular pita for me because I use bullets, try to use perfect spelling, and try my best at punctuation.
most people are going to destroy their home servers running these workloads