ericdotlee

With the recent release of Qwen-3 Omni I've decided to put together my first local machine. As much as I just want to pick up a beelink and flash it with Omarchy I think I want a bit more horsepower.

However, the internet seems littered with "clever" loca ai monstrosities that gang together 4-6 ancient nVidia GPU's (priced today to seem like overpriced e-waste) to get lackluster performance from piles of nVidia m60's and P100's? In 2025 this kind of seems like a waste or just bad advice to use hardware this old?

Curious if this find seems like a good source of info regarding staying away from Intel and AMD GPU's for local inference? Might do some training but right now more interested in light RAG and maybe some local coding.

Hoping to build something before the holiday season to keep my office warm with GPU's :).

Thanks!

What is llama-swap?

Been looking for more details about software configs on https://llamabuilds.ai

I've purchase 16 of these - cpayne is great! Hope he finds a US distributor to help with tariffs a bit!

Any reason you wouldn't opt for the 4090 or 5090?

Hi, I'm looking to transition from renting GPU's from RunPod to hosting some models locally - specifically qwen-2.5 and some lightweight VLM's like Moondream. It looks like the RTX 3060 12gb is a relatively good option but I don't necessarily have a lot of experience with pc hardware, let alone used hardware.

Curious if anyone here has a similar config of 1-4 RTX 3060s? Trying to decide if picking up a few of these is a good value or if I should just continue renting cloud GPU's?

Why is zog so popular these days? Seems really cool but I have yet to get the buzz / learn it.

Is there a big reason why Triton is considered a "failure"?

I've built a few small machines in my homelab - but I've been a huge fan of the Beelink mini ryzen PC's that DHH has been featuring with Omarchy.

That said - I don't think I want to opt for one of the Ryzen "ai mini pc's" they seem solidly a worse option than a 3090?

I've been toying with the idea of building a dedicated machine to continue working on my FPV flight control model.

So far I've just been renting gpu time but it's getting expensive. I also occasionally use qwen3-coder in my homelab but my headless "inference" machine is quite limited with an RTX 3080.

Curious if this build from llamabuilds.ai looks good? In terms of gpu etc? I'm maybe considering buying more GPUs in the future - hard to tell if stacking RTX 6000 ADA's is worthwhile!

Thanks HN!

I think this is going to change really fast - not in favor of ai companies or investors.

Initially, ChatGPT was kind of a cool toy that felt like something new but not really a threat. Now, even people who aren't engineers see the threat this has to destroy the dignity and financial stability of millions of people.

I like Ai - but at the same time I hope our country picks people over corporate profits... unfortunately I don't see that being likely.

It's wildly sad - but the number of people using this for concerning emotional needs use cases is troubling.

Companies like BetterHelp have not helped people improve really just training them to have a constantly affirming voice at arms length at all hours.

I honestly don't know what I would do if I was fresh out of school today or over 40.

That said, grinding through middling startup jobs also sucks.

The ability to get vc attention seems incredibly cliquey - not a game I really want to play again. On top of just wanting a normal / decent salary as a founder.

I usually stick to lava lamps

My favorite elixir project of all time now written in Rust.

Love to see it.

Have you guys added the ability to cleanse / watch command strings for sensitive items like secrets, keys etc? Seems easier than ever with advances in lightweight LLMs.

Hey Eric, I've been using trigger since April of this year!

It's a core tenant of my business and a handful of side projects. Wish you and your team the best!

My guess is they don't really know how to price it in yet - but also they seem to massively reduce headcount in areas where you can loftily make assumptions that "ai is boosting productivity"

Seems like hand waving and layoffs will have to stop before we get real data

Just curious, but I'm curious what these platforms are chasing? I assume a quick acquisition by an org like Salesforce building huge agentic tooling?

Any idea what triggered this in Southeast Asia? I think Vietnam just did the same thing with over 80M accounts. Seems like the IMF accused them all of harboring mass money laundering or offshoring schemes?

What a lot of these journalists don't realize is ai tools are the internet funnels of the future. People use ChatGPT not Google to source info. The way you get results is begging these tools to search for specific bits of info in order to get visibility.

Do you think vibe coded rust will rot the quality of language code generally?

This is incredibly cool, but I wonder when more of the AI ecosystem will move past python tooling into something more... performant?

Very interesting to already see rust based inference frameworks as well.

Humans are important - but I have to wonder how any of this will be enforced?

Shrinkflation and private equity really do ruin everything!