GLM 5.3 is probably the sweet spot open weights model if you want to go beyond deepseek flash or the new glm flash. I used it with pi and had a fairly good time, especially since it’s less touchy about cyber and whatnot than the US guys. It’s slightly behind Kimi in ability but it’s a lot easier to run it, I’d expect prices (and speed!) from third parties to be noticeably better.
Assuming you’re willing to drop a fat stack of cash on the upcoming Mac m5 ultra with 512 gb unified memory, you can even run it locally, quantized to 4 bit. Whether it’s even slightly reasonable, well, my wife would probably skin me alive but maybe yours is more understanding.
When we consider:
* LLM usage is new for the world
* Models are evolving quickly with high worldwide competition
* Hardware is evolving despite RAM shortages
Is investing a huge sum of money in equipment for local inference a wise use of money? Or are M5 Ultra and equivalently priced local inference hardware future-proof enough to be worth it relative to how the market is evolving? Maybe it’s all a question of what you’d spend otherwise on serverless or dedicated GPU spend…
It is absolutely not worth buying hardware to run models for purely (long term) cost reasons. For open weights models the economies of scale means the cloud beats local significantly and your payback time is like 10 years.
However there are other reasons (e.g. privacy) that might make it worth running locally for some people.
I think that's overly pessimistic. Here's [1] a video of somebody running it on a ~$6000 rig and getting around 14T/s for complex prompts (about double that for simpler prompts). Payback time is going to depend on your electric cost/consumption. In most domains cloud providers end up charging a significant premium rather than a offering a scale enabled discount, relative to local at retail costs. That will almost certainly end up being the case with LLMs as well, if it isn't already.
Furthermore we continue to follow the path that image gen neural networks took. In that domain hardware requirements reached a peak and then started sharply declining to where we are today where a plain old video card can rapidly generate images that took a supercomputer not that long ago. So it's reasonable to assume that performance of such a system could potentially even increase over time.
[1] - https://www.youtube.com/watch?v=ZWS2JVN2iBI
I think the biggest reason is to own the stack so your model can't be changed out from under you, but maybe I care about that too much.
> I think the biggest reason is to own the stack so your model can't be changed out from under you,
The concern would be future regulations that prohibit you from buying a hosted version of the model. Even that could be bypassed with a VPN to another country but it's more work to go through the payments.
As long as there is demand for a model, it will be hosted by multiple providers.
What if the model is hopelessly obsolete, and thus no demand, but I want that specific model? Owning the weights and hardware is not just solving for one problem. It eliminates all the classes of problems that occur outside of your building, if you have a solar and battery setup.
Also, on a more practical basis, what if the way it's served is bad. Maybe I want my specific KV setup, or ultra low quant for entertaining garbage at 200 tk/s
> What if the model is hopelessly obsolete, and thus no demand, but I want that specific model?
You can still find a lot of old and completely outdated models on OpenRouter. The providers can scale serving of models up and down as demand arrives, so models don't generally disappear. They're just kept in the mix and the clouds will allocate hardware to it if someone is willing to pay.
In the odd case that it disappears completely, buying the hardware 2 years from now is probably going to be a better deal. That wasn't true if you selectively check the time period before hardware got expensive, but as new hardware comes out we're going to start seeing Strix Halo and old Apple hardware hit the market as people upgrade. It's already happening.
There is a certain personality type that cannot tolerate any uncertainty and must lock everything in right now against all future possibilities. If you fit that description then there's nothing anyone can say to discourage you from buying your own hardware, but for everyone else I do not recommend buying hardware to self-host LLMs just to save money. I self-host and run a lot of tokens through my setup (non-coding work) but I'm not really saving money.
> There is a certain personality type that cannot tolerate any uncertainty and must lock everything in right now against all future possibilities.
I thought HN banned personal attacks. I'm in this sentence and I don't like it. /s
I just buy the good apple hardware because it's good, and it also happens to run local models. It's not as good for the dollar, don't get me wrong, but I'm not going to develop iOS without a mac, that's even more questionable than buying a strix or whatever.
Welcome to production software, where you really want to pin all uncertainties and dependencies, and roll back in case a major problem occurs.
Also, this makes me wonder if, by using a bicycle generator, and a local model at sufficiently low power consumption, you could directly claim to have produced the text in a really physical way. "Yes, I generated the electrons that made that text work by my own efforts".
The only reason I'm considering picking one up is I think we're not that far away from compute limitations in consumer hardware.
I live in a place where using VPN is illegal and akin to "terrorism" because why would you want to hide what you are doing. Only bad guys hide. So if you use VPN, you are a bad guy.
https://srinagar.nic.in/notice/immediate-suspension-of-virtu...
Phones are randomly searched on the streets and if VPN is found, arrested
https://www.medianama.com/2026/01/223-jammu-kashmir-vpn-ban-...
https://timesofindia.indiatimes.com/india/after-vpn-ban-in-k...
“Out of the 15 individuals identified, five were minors who were counselled and advised in the presence of their guardians, with emphasis on awareness, lawful digital conduct, and the consequences of violating lawful orders,” he added.
You do, there's like 20 providers for any model on openrouter. You can also just spin bedrock or gcp and download the weights for later if you're worried. It's never going to make cost sense when the token rate is so low with how expensive ram is
What if the internet goes away?
I'm actively uninspired to write high quality code when using Anthropic/OpenAI models given the high chance I'm a customer as well as used as dataset generation tool for them.
But currently cloud does beat costs of hardware ownership, particularly with ridiculously high RAM/GPU/SSD costs....again due to these same companies.
And compliance.
I think the privacy argument that keeps coming up is overrepresented. Certainly ZDR is enough for an absolute majority of use cases? I see so much talk about local inference but I doubt most of it has privacy as a valid argument (not arguing it doesn't exist). It's fun to do things locally though. I've tried it as well but cloud is just faster and cheaper.
These companies have displayed zero respect for everyone's intellectual property getting these models trained.
I think not giving them your complete trust is reasonable! I'm not saying zero trust, and ZDR is fine for most things but I understand the people who don't want to stream their whole codebase out token by token.
Then use other providers hosting open models. Companies and individuals already put their whole code base on the cloud. I'm genuinely interested in privacy-oriented use cases where ZDR is not enough.
I'm not that worried about the codebase itself. I'm worried about the fact coding agents poke around the terminal and system so much that there is almost a certainty that some of your other personal data ends up in the context somewhere which is getting logged in to a training dataset by random hosting providers.
ZDR is built on trust. Given that end-to-end encryption fundamentally doesn't work with LLMs, as they need the content to be unencrypted to operate on it[1], you have no way to prove that once your plaintext data is on somebody else's server they aren't doing whatever the hell they please with it. All you have to rely on is their pinky promise that they won't do anything with it. Trust is a valid option, much of our society runs on trust, but you can eliminate the need for trust whatsoever by running on your own hardware.
[1] Yes, I'm aware of experiments to operate on encrypted prompts, but these are only research attempts, not something that could actually be used with frontier models in production.
Privacy isn’t only, I don’t want anyone to have access to my data. It could also be, I don’t want anyone to know my use case because it’s niche and highly profitable.
I have a Strix Halo and dual 32GB GPUs in my desktop, that sit idle right now, because the electricity to run them and to cool them in 110F weather Texas is currently experiencing pretty much nulls any savings I might see over getting better models from cloud providers. While I mostly use Claude or Codex with subscriptions for agentic work, for API use DeepSeek has usually been my go to, but now I guess it's GLM 5.3 or the Flash version. And, for security work that Anthropic or OpenAI models are likely to refuse, I've been using Kimi K3 (also via subscription, though their subscription is extremely stingy), but I guess GLM is now the one for that, too.
Anyway, yeah, even at the prices I spent on my local AI stuff (I bought before RAMpocalypse really kicked into gear, so I bought old server GPUs for about $350 each and the Strix Halo for a little over $2k) it was never going to pay for itself; I just like to tinker. But, I can't imagine spending today's prices for hardware for local AI.
When the memory shortage ends, I'll be down to the Apple Store (or, more likely, clicking refresh on the Apple outlet every few days). But, until then, there continues to be a glut of cheap and free models in the cloud that are better than anything I can run locally and they're faster, too.
I wish Texas would write up a regulation allowing 'balcony solar' as I could easily generate 1000-2000w of solar in my small back yard to take a bite out the sizeable cooling bill I have.
Seems like it's easier to ask forgiveness than permission. And, I wouldn't bet on this legislature ever doing anything that would disempower fossil energy or reduce their profits, even a little bit.
Too hot and expensive to run right now but a great hedge for peace of mind against $200 subscriptions shooting up to the $4000* they should cost.
*$1000? $14,000? Who knows but everything in the middle there has been claimed.
Yeah, I guess, but it feels like there isn't really an opportunity for anyone to do that, given how competitive the market is. If Anthropic decides to demand API rates for everything (which would make my $100/month turn into a few thousand, I guess), I won't be seriously inconvenienced by switching to GPT. And, if both of the major American providers do a pricing collusion and GPT also becomes thousands of dollars a month to use, I can choose between Kimi K3 and GLM and so on. I'd rather use Opus 5 and Fable, but I'm not going to be seriously put out if I can't. We've got three or four open models to choose from that are as good as or better than Opus 4.8, which is Good Enough, and the competition isn't slowing down. We're seeing more new competitive models more frequently than even three months ago.
So, even though there are more models to run locally that can be useful for the stuff I do, it makes less sense now to do so than it did when I got it. There are more extremely cheap options, now, and it seems likely to continue to get cheaper and better and faster, while my local hardware will always be slow and hot and only gets better via software (which has roughly doubled the speed it can run stuff since I got it, but it seems like there's less room for improvement in software now, and even at twice the speed, it still kinda sucks to use local models interactively especially on the Strix Halo).
If they "should" cost 4k in the sense of marginal cost, then you will be spending more running the same at home, because your home hardware will always be less efficient.
There is a big difference in the cost of a 5-nines up time system in a heavily space constrained environment compared to a home hobby white box used for some coding. The GPUs alone cost 10x for the data center versions compared to the gaming versions even with similar specs.
The cost of online services is also largely a result of the cost of training (though hard to say exactly what that number is). Assuming you are using open weight models at home, you aren't paying for the training - someone else is.
> The cost of online services is also largely a result of the cost of training
OpenRouter prices are somewhat simmilar to Antrhopic/OpenAI API prices. So I conclude that the hardware plus operating margin alone can genuinely produce prices way above what you'd pay if you had a subscription. Of course the primary unkown factor is average token use per subscription. Without that it's all wild speculation.
So far I don’t regret buying an M1 Max device with 32Gb of RAM. The models available for it keep getting better (running just about okay for interactive use) and 400 GB/s of bandwidth is still considered a lot.
The models are currently improving much faster than the hardware and this doesn’t seem to have plateaued yet.
Cool! I'm thinking about a local set up. What's your usual tokens/second rate?
Not OP, but I’m running local models on a M1 Max as well with 64GB RAM.
It varies by model, but I’m getting 50-60 t/s with Qwen 3.6 35B and Qwen 3 coder 30B.
I’ve also used Qwen 3.8 27B but I get 10t/s on it.
It’s useable in some use cases, but I rely mostly on my $20 Claude subscription.
That's so cool. I wonder if the regular M5 can run those models too.
Jalapeno is matching or very near Vera Rubin at 1/4 the power. I would not buy hardware now.
OpenAI have only just announced it and have every reason to hype it up.
Could be a long time till gets released
Only reason to spend a bunch of money on hardware to run LLMs locally is if it's a hobby to you to an extent that even renting the GPUs temporarily won't satisfy you.
Or if you need stuff that APIs don't / can't provide. Or for future proofing your workflows. Running things locally gets you "the same thing" in perpetuity, while APIs might change, models can be deprecated and features can be removed.
Cybersec is also hit and miss, depending on what provider you choose, verification systems and all that jazz. Also, running locally allows you 100% data privacy, in any situation and for whatever usecase you might have. ~100k for hardware for a small team of devs to code locally is not that expensive in the grand scheme of things.
Lastly, local models allow for training / finetuning on your own data and processes. $/tok is not everything for everyone. Sometimes you can take a hit on value / speed if you get something else that matters for you.
That's basically the question I'm trying to answer.
If you're paying Anthropic or OpenAI to use their models, harness, governance, etc., I could see the local inference potentially coming out ahead. They're already starting to ratchet down what your money gets you on their platforms, and that can be expected to continue as the leaders of those companies continue to seek the road to the El Dorado that is being a trillionaire.*
If you're looking to get into the guts of AI development instead of having it handed to you by a provider, that's where it gets murky. I'm wanting to write some sort of agent that does things and get into making outputs consistent in the like, and I'm not sure whether to host something on GCP or buy an M5 Mac.
*Note: El Dorado is a mythical city and many people died trying to find it.
Tools vs services in my mind. There is no guarantee any provider will continue to do what they are doing for you at the price they are doing it.
The object permanence of not having to reinvent the world every time a model gets sunsetted has value.
> Tools vs services in my mind. There is no guarantee any provider will continue to do what they are doing for you at the price they are doing it.
with open models, there is ecosystem/market of providers, where you can easily switch to provider you like
Until there's an executive order that blocks one model from being served.
With competition we kind of have guarantee up to what providers can do, they don't have that much control, the most radical thing they can do is to go bankrupt.
Have you already forgotten the Fable drama that happened just two months ago?
Self-hosting won't protect you from getting locked out of a closed weights model, because you can't self-host it even if you have the hardware.
Yes, I remember recurring extensions on plan inclusion then becoming permanent - that's my point.
Do You have guarante any electricity price?
Maybe not them specifically, but for many people with solar as an option, yes.
Part of it is knowing that whatever sort of enshittification the cloud providers do, my local programming environment won’t ever be less effective than it is today locally. It’s the same reason my entire development stack from editor to compiler is open source. I don’t need to modify it today, but I always must retain the option to do so later.
There are several things I do in my life that only pay off in the event of a big disaster, like an extended internet outage, civil unrest, supply chain disruption, war, etc.
I like to be able to do the things I do even if offline for weeks.
I spent a lot of money for more flash in my iPad Pro so I can keep all of offline wikipedia and OSM in it, for example, along with tons of books. It’s sort of like being a digital prepper. (Being a prepper is a spectrum, from anyone who keeps food in their pantry to people building bunkers under their house - how much you invest is a personal prudence and threat modeling decision.)
Also, privacy. And when I got the Mac Studio the 512GB was only $15k, which is dirt cheap for that much VRAM.
> Part of it is knowing that whatever sort of enshittification the cloud providers do, my local programming environment won’t ever be less effective than it is today locally.
Is that true though? Many of the core LLMs need to be retrained as languages evolve to incorporate changes (language specifics, compilers, tooling, etc.). To some degree this can be handled via context injection in a variety do forms (agents looking up documentation and so on) but inevitably it’s not stationary in time, just as your OSS stack (probably) isn’t (depending on the languages, technologies, and use cases).
So your hardware is to some degree dependent on the good merit of groups like Z or Alibaba or whomever pushing out updated open weight models that dumped loads of capital into to train. You can keep using the existing models but at some point I suspect they’ll start to have more friction due to dated specs in language and so on. Again there are tuning and ways of layering this information on, and in theory you can even do some training on your own but I don’t think it’s as stationary as being portrayed here.
Those updated open weight models may not always be there (updated on new data). The usability of them is probably fairly long to be fair, but I suspect you’re going to see explosion in everything from libraries to languages etc due to LLMs so even the rate of change across your OSS stack may cause these models to be dated quite quickly, at least in the core model which will require layering fixes.
To be clear I’m on the fence thinking about much of the same issues and as close as I am to pulling the trigger, I keep thinking of very valid counter arguments as to why it’s me just wanting this thing I own. Which may be enough.
With every newly released open weight model, the clock on the issues you describe is reset. I can see a marketplace arising for paid updates to common lines of open weight models, which will incentivize those with the hardware to train to fix the problem for those who only have the hardware for inference.
I would say when this comes to pass, we are already 5 years along?
> Part of it is knowing that whatever sort of enshittification the cloud providers do, my local programming environment won’t ever be less effective than it is today locally.
I think this is quite understated. It basically is freedom from a growingly antagonistic relationship between you and some remotely hosted API managed by faceless corporates at the whims of their board, shareholders and governments.. It really is such a mental burden to need to constantly manage this relationship (watermarks, silent downgrades, random false refusals, downtimes, model sunsets, changing ToS's, fucking ads). These companies will need to squeeze you for every cent that they can before open-weight models are simply good enough for the valuable tasks we can throw at them.
To have your own hardware is to no longer have this mental burden.
In terms of pure tokens per dollar, absolutely not worth it.
That said, when I bought my pair of Sparks, the best model I could run on it was GPT OSS 120B. That has an AA score of 24.
Today, the best model I can run on them is GLM 5.3 Flash at Q4, AA score 57. Just still out on GLM 5.3 mixed quant.
So from that perspective, they are many times better value than when I bought them, and will likely continue to increase in value.
> GLM 5.3 Flash at Q4, AA score 57
That AA score is for the original model only
Then take DeepSeek V4 flash with AA score 52. Runs unquantized on 2x DGX spark with 1M context.
Or Qwen 3.8 27B, AA score 52 (which is utterly insane given the size of this model); I have been testing Qwen 3.8 27B since a week now, as an intensive GLM-5.2 and Opus 5 user - I can say that I just can't believe my eyes i.r.t. to how good this model is.
I have just built an Epyc with 512gb DDR4 3200 RAM for a "reasonable" price and I'm hoping to have a setup with GLM as the architect and Qwen 27b/Next Flash as the implementer. This is 1/5 of the price of the Mac, but also probably 1/5 of the speed lol.
I’ll be very curious what you get with DDR4. I also almost went that way. I have an Epyc DDR 5 rig and the best I see is 10 tok/s. Caveat being that’s at Q8 and a 4090 doing pre fill so it could be pushed up.
The surprising thing for me is how much work you will need to cool the banks if you’re near your memory ceiling. My memory starts soft throttling at about 74C (dies may be hotter, that’s the bank temp) and will turn down speed to try to stay below 80.
Happy to send my llama.cpp config settings if you want it.
I am getting 10t/s on unsloth's Q3kxl with 2x3090s@250w. It's enough for me for now. I will probably upgrade the GPUs down the line. DDR5 would have made the price of the machine double and I just wasn't prepared to pay that much.
Temp wise, no throttling, surprisingly cool.
Typically computers with these larger memory amounts have fans that scream like a banshee trying to move impossible amounts of air over the memory and CPU. Getting something both cool and quite can be a bit difficult.
I was running one of the older llamas (3.1 I think?) at slow-ish (10-20 tok/sec at Q4?) but OK speeds on 12 year old DDR3 ECC Xeon machine
I find 10 to be very usable. It’s not (that) interactive but it chews through tasks. I let Kimi churn away at 4 overnight and it gives good results that are ready for me in the morning.
Depending on which Epyc you got it might be slower than 1/5 of the speed.
48c 7643. I'm getting about 10tps @Q3kxl with 2x3090s.
Curious about that price, if you don't mind sharing a ballpark
About 5k with RAM and GPUs bought used. Eastern Europe.
I have a dual epyc + 1TB RAM. I could push glm 5.2 to 7 tok/s CPU only.
It’s not unified ram? I.e VRAM so it will struggle
I'm getting about 10tps @Q3kxl with 2x3090s.
Honestly I suspect neither of them will be performing terribly well but with DDR4 3200 RAM I wonder if you'll be counting tokens per second or seconds per token. I mean, you do at least get a lot of memory channels at least, compared to consumer PCs. I am curious to hear what performance you get, I feel there is not enough information out there on what different setups manage to eek out.
The fastest I was able to get my Threadripper 3960X + 2x 3090s + 256GB DDR4-3200 to run a 2-bit quant of GLM-5.2 was 8 TPS. I would expect to be in seconds-per-token territory for a pure-CPU 4-bit quant.
One thing I'd like to try is MoE offloading: I have 2x32 GiB of VRAM and 128 GiB of DDR5 running at 4800 MT/s (only 2 channels though). I've seen people post difficult to believe MoE offloading results albeit a decently long time ago with older models. Maybe there is a quant that would fit with MoE offloading?
That said, I am guessing my problem is not enough RAM - but this poor consumer platform struggles to do memory training with 128 GiB as it is.
Now I surely regret not having gotten Threadripper and 256 GiB of RAM in the before-times.
My measurement was with MoE offloading, but there's only so much you can keep on-GPU with a 200GB quant and 48GB of VRAM. It's hard to overcome the CPU/RAM bottleneck.
For what it's worth, all of my hardware was used; I think, all-in, I'm probably at around 3k-4k USD? Not cheap, but also not the worst for something relatively versatile.
Ah, I see - so MoE offloading is no savior. A shame but no surprise either.
With a 4-bit quant of GLM-5.2, I can get about 0.8-1.1 tok/s on an underclocked dual Xeon E5-2698 v4 with 512GiB of DDR4-2400. I think it was specifically a Q4_K_M quant. Of course, the time-to-first-token is absolutely atrocious.
Which is completely insane for a ten year old configuration.
What model are you interested in? DS Flash 0731@Q4KXL I'm about 25-30tps. Same as the new Qwen3.8 Flash Next. The new GLM 5.3Q3KXL at 10tps. I've got 2x3090s which I didn't mention in the original message.
It IS crazy to drop big money on any AI rig right now imho... the size of models and the cost to run them is falling through the floor as we speak.
I'm happy with all of the competition in the APIs on openrouter... I watch that like I used to watch the stock markets, lol. It's great fun.
One could also run it locally on a used dual xeon (or amd-equivalent) server with 512GB RAM, albeit slower, if you have a useful workflow for it that's like "take this day's efforts and run it through various analysis agents", combined with giving it one-shot tasks/modules to build overnight. You would want a place like a garage or basement to put the server because it'll be loud.
> "dual xeon"
Does inference make full use of the memory bandwidth in a NUMA system?
Memory throughput performance is better than many equivalently priced (talking about the cheaper end of the used/refurb market here) single socket systems because each CPU is talking to its own banks of RAM.
Using an example of llama-server on a 256GB (each CPU is attached to 128GB) system running qwen 3.8-flash-next Q8, which takes up about 188GB with the model and context, it's not that the inference engine 'knows' about NUMA, but if you use --load-mode mlock to load the whole thing into memory at once at the time llama-server launches, the kernel will distribute it relatively evenly across the memory connected to both CPUs.
You'd also likely spend far more in electricity than the API cost of processing the prompt(s)
yes, though for some uses, not sending data anywhere to third parties has its own value which is harder to measure.
Well if you did get the m5 ultra could you obliterate the guardrails and then your wife can ask it pertinent but unsafe questions about how to punish you. Seems doable.
Its reasoning leaves a lot to be desired :(
Though I appreciate how good it is at "solid" grunt work and at that price (in fact I am paying the grandfathered subscription price; mostly).
I am planning to let go for my Claude AI subscription which I now use only for "planning" and maybe use that via Open Router as PAYG (at to try how it ends up). But god glm is bad at "talking" and "responding" anything prose. Not only quality but it's almost impossible to tune it and make it let go of its habits and biases and enthusiasms which often result in too many too and fro.
So I sometimes wonder at what point that starts becoming the cost and mental hassle. Maybe it's not there for me yet.
I get some appeal of running locally, but isn't it just easier to rent cloud hardware and run whatever model you want to run?
There's certainly a mental difference between a computer you can use as much as you want for a fixed upfront cost vs a rented server you are being billed by the hour for.
But the cost difference between api and self hosted is so incredibly large now it's almost impossible to ignore the fact self hosting is a terrible deal. I'm waiting things out until the dust settles on what the required specs are and consumer hardware gets cheaper/more capable.
[flagged]
Not every tech worker is making top-tier US salaries. For some (I suspect not few) people on HN that $20,000 Mac is almost a year's salary.
and even if you were making such a salary, the quesiton of if the investment on hardware to run llm's locally is still a big if, its OK if you buy the HW cause you'll use it and you get the extra capability as a nice extra, but doesnt make sense to spend so much when you could just get 200$ subs with almost infinite SOTA tokens a month etc (if you dont need the local/privacy aspects of it)
You are allowed to have an opinion on her 20k bag addiction