A guide to local coding models • Hacker News Board

Re: A guide to local coding models

#361

Post by 2001zhaozhao » Tue, Dec 23, 2025, 11:27 PM UTC

rester324 wrote: post #219

2001zhaozhao wrote: post #165

Under current prices buying hardware just to run local models is not worth it EVER, unless you already need the hardware for other reasons or you somehow value having no one else be able to possibly see your AI usage. Let's be generous and assume you are able to get a RTX 5090 at MSRP ($2000) and ignore the rest of your hardware, then run a model that is the optimal size for the GPU. A 5090 has one of the best throug…

These are the comments of the people who will cry a f@cking river when all the f@cking bubbles burst. You really think that it's "$300 total to serve the same amount of tokens as a 5090 can produce in 1 year running constantly"??? Maybe you forgot to read the news how much fucking money these companies are burning and losing each year. So these kind of comments as "to run local models is not worth it EVER" make me ch…

If I were predicting the bubble to burst and API prices to go up in the future, wouldn't it be much better to use (abuse) the cheap API pricing now and then buy some discount AI hardware that everyone's dumping on the market once the bubble actually does burst? Why would I buy local AI hardware now when it is at it's most expensive?

Re: A guide to local coding models

#362

Post by lodovic » Wed, Dec 24, 2025, 6:15 AM UTC

ayewo wrote: post #242

lodovic wrote: post #183

Earlier quoted context omitted.

I actually get more mileage out of Claude using a Github Copilot subscription. The regular Claude Pro will give me an hour or up to 90 minutes max, before it reaches the cap. The Github version has a monthly limit for the Claude requests (100 "premium requests") which I find much easier to manage. I was about to switch to the max plan but this setup (both Claude pro and Github Copilot, costing 30 a month together) wa…

In practice, how does switching between Claude and GitHub Copilot work? 1. Do you start off using the Claude Code CLI, then when you hit limits, you switch to the GitHub Copilot CLI to finish whatever it is you are working on? 2. Or, you spend most of your time inside VSCode so the model switching happens inside an IDE? 3. Or, you are more of a strict browser-only user, like antirez :)?

I always start in the Claude CLI. Once I hit the token limit, I can do two things: either use Copilot Claude to finish the job, or pick up something completely different, and let the other task wait until the token limit resets. Most importantly, I'm never blocked waiting for the cap.

Re: A guide to local coding models

#363

Post by unethical_ban » Wed, Dec 31, 2025, 7:08 PM UTC

Workaccount2 wrote: post #12

I'm curious what the mental calculus was that a $5k laptop would competitively benchmark against SOTA models for the next 5 years was. Somewhat comically, the author seems to have made it about 2 days. Out of 1,825. I think the real story is the folly of fixating your eyes on shiny new hardware and searching for justifications. I'm too ashamed to admit how many times I've done that dance... Local models are purely fo…

There is a cultural component to privacy, and insulting people who want a technical assurance that their queries are under their own control is a way to work against privacy.