To me, most local models work just fine for anything you can be patient for. If I want something quicker, I will go to a SOTA model via API, but with multiple 3090s, I have never really needed a hosted model for a lot of my experiments.
For code, they are great, but for creativity for NPC controllers, they leave something to be desired, but work well enough for testing, so I don't burn tokens until I'm actually playing my games.
But nothing one-shots a prototype better than Fable 5. I can have a prototype built in 30 minutes, hooked up to my local LLMs and Claude Code is very good at testing the interactions and even tuning the prompts of the NPCs for better experiences.
Having multiple 6 year old cards doesn't seem like it's that big of burden for local LLMs.
I get that a lot of people don't have them. And a single one can be VERY performant. And the smaller models like a 7B can run on much smaller hardware like a mid-range [3|4|5]060.
My entire AI Dev Box cost $4500 in parts. 128GB RAM, i7-10700, 1TB and 2TB SSD, and 2x 3090s. Today's prices and inflation have definitely made that price tag seem a lot better than it was, but it was an investment in all things GPU that were happening in 2020 (crypto, blender, image gen), then LLMs exploded.
It seems roughly similar to the pricing level of personal computers in the early eighties (i.e. IBM PC and Apple Macintosh). I’d expect prices to come down significantly over the next few years. Not so much in the next year or two, but after that.
Just like for warships, the complexity and cost of building cutting edge hardware has grown exponentially up to a point where a significant chunk of the world's computing is dependent on 2 companies: ASML, TSMC. We shouldn't extrapolate linearly from examples from the 80s.
No, but I wouldn’t expect it to stagnate like with Intel in the 2010s either. Maybe the biggest caveat is that most people will be fine with using cloud providers, so the market for non-server hardware won’t be subject to as much competition.
There's a non-small contingent who lucked into the periodic games machine upgrade at the right time to snag a {3,4,5}090 rig just before everything exploded. It's a small contingent now but it was less so then. And now those people can add a second card for roughly what that whole system would have cost new originally.
So will the stock of 3090s, as well as their ability to run contemporary local models. And there will be no supply of newer equivalents of those GPUs, because NVIDIA has since wisened up, and is using the very capabilities you need for local LLMs as market segment differentiator.
I don't think there is tunnel vision. I'm just saying that I have a couple 3090s I invested in a handful of years ago, and they are still going strong today as multiple GPU-needing technologies emerged.
I'm not saying everyone has to run local LLMs, because the APIs are in a race to the bottom, and my $10 of OpenRouter credits I bought months ago is down to $8.94 because most models give you MILLIONS of tokens for a US Quarter.
This is tunnel vision. The percentage of people who could afford the hardware you could at the time you back it so vanishingly small. I do not know a single non-tech person who has multiple graphics cards in a single computer.
And right now the demand for GPU is far outpacing the supply, even with factories at full production, which is keeping prices high and out of reach of most people. But unless something happens to shut down the factories (not impossible, but hasn't happened yet), eventually production will catch up to demand and prices will return to sane-ish levels. Won't happen this year, almost certainly not next year... but I would be shocked if the current high prices were to persist for a decade. Eventually the percentage of people who can afford that hardware will grow to be a decent chunk of the computer-owning population. And they'll be following READMEs written by the early adopters, for installing open-source harnesses to work with open-weight models.
My personal expectation is closer to 5 years than 10, which is why I wouldn't touch Anthropic or OpenAI stock with a ten-foot pole, personally, no matter how high their theoretical valuation is. Because their business model is doomed in the long run.
Newer cards aimed at consumer market are not capable of being used for local models the way 3090s are. That's on purpose: this capability is now used to price-differentiate between "normies playing games" and "companies in data center business".
For now. That won't last forever. Yes, it'll take quite some time to work through the current production backlog, which is why I'm predicting five years, not one or two. But the trajectory has always been "new video card comes out, game devs push the limits of what it can do, gamers buy new card so the hot new game can run faster, rinse and repeat". And that includes wanting more VRAM so the game can load more of the scene at once, load higher-res textures, etc.
Which means it's inevitable that eventually, even the consumer game market will be buying GPUs with 32 or 64 GB of RAM. And there are decent models that will run at that size. Even the "normies playing games" market, as you call it, will end up with the capacity to run local models. It'll take a few more years than it would have if the data-center companies weren't trying to buy up all the GPUs, but it's not like gamers are going to stop wanting to play games. So in the long run, Anthropic et al are still going to have to figure out how to deal with competition from local models that run on your gaming video card. Which won't ever be at parity with the models that take terabytes of VRAM to run, but are very rapidly approaching "good enough for what most people want to do".
I mean, I'm not rushing out to buy that kind of hardware myself, but it is a matter of perspective. People commonly spend an order of magnitude more on a car, and that's just the sticker price.
I keep coming back to this: why do I need to run a local model on my own GPU? Open models can run in dedicated clouds and while, yeah, they may be more expensive per token than my own GPU, when accounting for depreciation, energy usage, and opportunity cost (money not spent on my GPU will instead sit in my portfolio appreciating with its particular blend of returns), I'm pretty sure I break even or even net lose money with a GPU.
Don't get me wrong, there are advantages to a fully local model in that, I can have agents looping 24/7 even when my internet is not working. But this is niche enough that if I had to price the advantages they don't seem worth it.
If I'm willing to pay the Openrouter tax, I can fire up Openrouter today and just get access to whatever model I want, and still pay a fraction for tokens as what I'm paying with the big guys.
Unless you value privacy, pay for openrouter. You still get the benefits of cheap tokens and programmatic usage.
3090 pricing is something of a wild card. Since the only big-mem consume cards are the xx90s, and a 5090 is pushing $5000, resale value has gone way up. The bottom hit ~$700 last year. It's still a very good GPU, if power hungry.
I got a great deal on ~72 TB of NVMe right before storage prices shot up, doesn't make it any less ridiculous that I have it or any more relevant to people talking about building a NAS now. 99% of people, even in tech, do not have the stupid amounts of hardware people like us hobby on.
Most people in the US have a car, and the average new car is $40,000. Hell where I live a middle class consumer will spend double that on a Boat or an RV and think nothing of it. These aren’t elite tech workers.
It’s not unfathomable that if a personal, generally intelligent local AI provides enough utility and doesn’t require you to tweak CLI flags millions of Americans would want one.
There are many payday loan operators and those willing to sell predatory loans to those workers you mention buying boats or RVs. I've yet to see a payday loan open up in SF to help tech workers buy hardware.
Most people in the US don't drive a new car, and used cars can be had for far less than $40k. An $80k purchase would be just shy of the median annual household income -- anyone who thinks nothing of that has financial resources far above typical. You are in a bubble.
An $80k purchase is far more affordable when you're looking at an 84 month loan. You trade in your current $20k truck with $30k in debt on it for your $80,000 car, get a couple grand in incentives and a $10k down payment, and boom you're only looking at a bit under $1,200/mo in payments. The median household is bringing home ~$84k before taxes, hypothetical person lives in a no income tax state, they take home ~$5k/mo. Easy peasy, its not like you were planning on taking any vacations anyway since you're always working.
What matters is you've got the Duramax HD King Ranch TRD Big-Boy machine. Doesn't matter the cost. You can tow anything, drive anywhere, do anything, and do it all in comfort. Other than parking in a normal parking spot comfortably. Or even park it in your own garage at home.
I've seen this exact scenario many times personally.
Spending that kind of moment on a product that gives you personal happiness for years up to decades and then will still have residual worth, which people save up for ages for, is an entirely different proposition than buying a product that may make you faster professionally, but which in the short time can also be achieved by a few dollars worth of subscriptions to a hosted model for even greater effect.
Americans by and large don't do that. Much of the population engages in discretionary spending with debt instruments. Combined with mass innumeracy, they're all oblivious to the true cost of their purchases because they only think of the monthly payment.
It was a 96 core gen 4 epyc+supermicro board build with consumer NVMe drives on 1x16->4x4 "dumb" bifurcation cards. I had to get a few MCIO-> PCIe adapters as well to get the full lane coverage. Mounted in a standard EATX compatible consumer case with a consumer PSU and a lot of Noctua fans - surprisingly cool and quiet for what it is.
Motherboard+CPU I got from Ebay. Rest from the best MicroCenter/Amazon/Walmart deal of that day. Bought juuuuust before the AI pricing apocalypse, largely by pure chance.
They cost more to run than hosted anyway. But that isn't the point of having them. They are a playground, a backup when the internet is down, or claude is down. They can render Blender scenes pretty well. They play any game I want.
You can do each of those at various hosts and own nothing. Or own a couple "over priced" cards and do it all at home on battery power for a few hours while the power is out.
BigCos you are referring to are earning their money doing state of the art research, not so much from your financial and medical data. That was the age of Internet ads, which was over since AdBlock was created for anyone concerned.
> You could sell those and have enough money to pay for hosted inference for years.
From a quick search a 3090 looks to go for about 1500-2000 USD. So let's say $4K for two.
I'm spending far over $1K/month (employer-paid) on cloud AI, so if that could be anywhere near comparable we're only looking at less than a few months break-even.
Less really, because some months are more expensive. This month I'm up to ~$500 and it is only day 4 of this month.
I keep seeing this comment. This is _hacker news_ where, back in the day, people just hacked on things, because it was a hobby. They weren't "moneymaxxing" or desperately trying to be as insanely efficient as possible. They hacked on stuff with a can of surge at 3am because it was fun.
Your comment is like a meta comment of "LLMs are generating everything, after a while the ouroboros will eat itself. (Which I agree with)" If people aren't hacking on this shit just because, you have completely conceded control of software to a handful of sociopaths, and open source software is dead.
Back in the day the business backing this platform wasn't incubating companies like Flock (YC S17). I think the increased focus on "moneymaxxing" in the community reflects a similar change by its owners.
Not really. 2 years ago that was a pretty normal amount of GPU hardware for a hacker or gamer. It's all relative. They are not accessible to most people yet, but for someone that cares and is a technologist? Likely accessible.
I have trouble getting simple extraction to work sometimes. I have a block of text describing people and their roles at a company and their ages, and i asked for structured results of an array of these things with the text span that it appears in and all i can say is: nope.
I've done pretty decent local prose->json extraction using Qwen and Phi and Gemma.
I'm sure most of it comes down to prompts, and all of them run over 100tps on a 3090. Smaller cards will likely be slower, but Qwen3.5 9B is small enough to fit on most consumer cards.
For code, they are great, but for creativity for NPC controllers, they leave something to be desired, but work well enough for testing, so I don't burn tokens until I'm actually playing my games.
But nothing one-shots a prototype better than Fable 5. I can have a prototype built in 30 minutes, hooked up to my local LLMs and Claude Code is very good at testing the interactions and even tuning the prompts of the NPCs for better experiences.