Live data from Hacker News

Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

news.ycombinator.com

341–350 of 379 posts

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#341
post #312

The short answer is "batch size". These days, LLMs are what we call "Mixture of Experts", meaning they only activate a small subset of their weights at a time. This makes them a lot more efficient to run at high batch size. If you try to run GPT4 at home, you'll still need enough VRAM to load the entire model, which means you'll need several H100s (each one costs like $40k). But you will be under-utilizing those card…

> These days, LLMs are what we call "Mixture of Experts", meaning they only activate a small subset of their weights at a time. This makes them a lot more efficient to run at high batch size. I don't really understand why you're trying to connect MoE and batching here. Your stated mechanism is not only incorrect but actually the wrong way around. The efficiency of batching comes from optimally balancing the compute a…

You’re right, I conflated two things. MoE improves compute efficiency per token (only a few experts run), but it doesn’t meaningfully reduce memory footprint.

For fast inference you typically keep all experts in memory (or shard them), so VRAM still scales with the total number of experts.

Practically, that’s why home setups are wasteful: you buy a GPU for its VRAM capacity, but MoE only activates a fraction of the compute each token, and some experts/devices sit idle (because you are the only one using the model).

MoE does not make batching more efficient, but it demands larger batches to maximize compute utilization and to amortize routing. Dense models batch trivially (same weights every token). MoE batches well once the batch is large enough so each expert has work. So the point isn’t that MoE makes batching better, but that MoE needs bigger batches to reach its best utilization.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#342
post #117

Earlier quoted context omitted.

Googles bread and butter is advertising, so they have a huge interest in keeping things in house. Data is more valuable to them than money from hardware sales. Even then, I think that their primary use case is going to be consumer grade good AI on phones. I dunno why Gemma QAT model fly so low on the radar, but you can basically get full scale Llamma 3 like performance from a single 3090 now, at home.

It’s my understanding that google makes bulk of ad money from search ads - sure they harvest a ton of data but it isn’t as valuable to them as you’d think. I suspect they know that could change so they’re hoovering up as much as they can to hedge their bets. Meta on the other hand is all about targeted ads.

Right so keeping things in house and seeing what people are asking Gemini would be probably better for them?

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#343

Earlier quoted context omitted.

Googles bread and butter is advertising, so they have a huge interest in keeping things in house. Data is more valuable to them than money from hardware sales. Even then, I think that their primary use case is going to be consumer grade good AI on phones. I dunno why Gemma QAT model fly so low on the radar, but you can basically get full scale Llamma 3 like performance from a single 3090 now, at home.

https://www.cnbc.com/2025/04/09/google-will-let-companies-ru... Google has already started the process of letting companies self-host Gemini, even on NVidia Blackwell GPUs. Although imho, they really should bundle it with their TPUs as a turnkey solution for those clients who haven't invested in large scale infra like DCs yet.

Its the same format as other software - you release the actual software for free but offer managed services that work with that software way better and easier.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#344

Earlier quoted context omitted.

Yes. Google is probably gonna win the LLM game tbh. They had a massive head start with TPUs which are very energy efficient compared to Nvidia Cards.

Google will win the LLM game if the LLM game is about compute , which is the common wisdom and maybe true, but not foreordained by God. There's an argument that if compute was the dominant term that Google would never have been anything but leading by a lot. Personally right now I see one clear leader and one group going 0-99 like a five sigma cosmic ray: Anthropic and the PRC. But this is because I believe/know that…

Everyone seems to forget about Mu Zero which was arguably more important than transformer architecture.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#345

Earlier quoted context omitted.

Someone's take on AI was that we're collectively investing billions in data centers that will be utterly worthless in 10 years. Unlike the investments in railways or telephone cables or roads or any other sort of architecture, this investment has a very short lifespan. Their point was that whatever your take on AI, the present investment in data centres is a ridiculous waste and will always end up as a huge net loss…

If it is all a waste and a bubble, I wonder what the long term impact will be of the infrastructure upgrades around these dcs. A lot of new HV wires and substations are being built out. Cities are expanding around clusters of dcs. Are they setting themselves up for a new rust belt?

There are a lot of examples of former industrial sites (rust belts) that are now redeveloped into data center sites because the infra is already partly there and the environment might be beneficial, politically, environmentally/geographically. For example many old industrial sites relied on water for cooling and transportation. This water can now be used to cool data centers. I think you are onto something though, if you depart from the history of these places and extrapolate into the future.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#346

Earlier quoted context omitted.

They probably are right, but a counter argument could be how people thought going to the moon was pointless and insanely expensive, but the technology to put stuff in space and have GPS and comms satellites probably paid that back 100x

It's not that going to the Moon was pointless, but stopping after we'd done little more than planted a flag was. Werner von Braun was the head architect of the Apollo Program and the Moon was intended as little more than a stepping stone towards setting up a permanent colony on Mars. Incidentally this is also the technical and ideological foundation of what would become the Space Shuttle and ISS, which were both also…

I’ve been enjoying that Apple TV show with alternative history as if we’d kept going. It’s kinda dumb in parts but still fun to imagine!

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#347

Earlier quoted context omitted.

Cooling BTUs already take the coefficient of performance of the vapor-compression cycle into account. 4w of heat removed for each 1w of input power is around the max COP for an air cooled condenser, but adding an evaporative cooling tower can raise that up to ~7. I just looked at a spec sheet for a 230V single-phase 12k BTU mini-split and the minimum circuit ampacity was 3A for the air handler and 12A for the condens…

Well I don't know why that unit wants so many amps. The first 12k BTU window unit I looked at on amazon uses 12A at 115V.

That is probably just bad data entry at Amazon. I don’t ever trust the specification data on Amazon, I look for the manufacturer’s spec sheet/cutsheet.

In this case, 12A is the maximum continuous load allowed on a 15A breaker. The unit itself probably uses between 900-1000w (7.5A to 8.3A), the spec sheet might say 12A to encourage a dedicated circuit for the A/C unit which then gets added to Amazon’s specs on their website.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#348

Earlier quoted context omitted.

It's not that going to the Moon was pointless, but stopping after we'd done little more than planted a flag was. Werner von Braun was the head architect of the Apollo Program and the Moon was intended as little more than a stepping stone towards setting up a permanent colony on Mars. Incidentally this is also the technical and ideological foundation of what would become the Space Shuttle and ISS, which were both also…

I’ve been enjoying that Apple TV show with alternative history as if we’d kept going. It’s kinda dumb in parts but still fun to imagine!

For All Mankind. I tried getting into that, but the identity politics stuff (at least in first season) was way too intense for me. I'm not averse to it at all in practice (Deep Space Nine is one of my favorite series of all time) but, for me, it went way beyond the line from advocacy to preachiness.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#349

Earlier quoted context omitted.

https://www.cnbc.com/2025/04/09/google-will-let-companies-ru... Google has already started the process of letting companies self-host Gemini, even on NVidia Blackwell GPUs. Although imho, they really should bundle it with their TPUs as a turnkey solution for those clients who haven't invested in large scale infra like DCs yet.

Its the same format as other software - you release the actual software for free but offer managed services that work with that software way better and easier.

Yeah but those are on Google's managed cloud, and not onprem. But that recent announcement has been specifically for Google Distributed Cloud, which is huge.

My point was a bit more specific though. To elaborate, I know of a number of publicly traded companies (USD $200M+ market cap) globally which have identified use cases for onprem AI and want to implement them actively but cannot, because they lack the knowhow to work with onprem, and hiring talent to implement that is just extremely expensive. Google should simply provide it as a turnkey bundle and milk them for it.

Re: Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

#350

Earlier quoted context omitted.

> So I simultaneously can tell you that its smart people really thinking about every facet of the problem, and I can't tell you much more than that. "we do 1970s mainframe style timesharing" there, that was easy

But that’s not accurate. There are all sorts of tricks around KV cache where different users will have the same first X bytes because they share system prompts, caching entire inputs / outputs when the context and user data is identical, and more. Not sure if you were just joking or really believe that, but for other peoples’ sake, it’s wildly wrong.

Really? So the system recognises someone asked the same question and serves the same answer? And who on earth shares the exact same context?

I mean i get the idea but sounds so incredibly rare it would mean absolutely nothing optimisation wise.

Post reply on HN