Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM-5.3 is now open-weight

huggingface.co

Post reply on HN
Print view View original

201–210 of 296 posts

Re: GLM-5.3 is now open-weight

#201

Post by cogman10 »

Philpax wrote: post #61
nkmnz wrote: post #25

I'd like to ask Sam Altman if he still thinks that it's too dangerous to publish GPT-3. I mean, no one would use it, but what is his reasoning for not publishing it now, in 2026?

There are risks associated with releasing historical proprietary models that were not designed for open release: - It is trivial to extract samples of the training data that was used, which can bolster existing lawsuits/foster new ones. - Older models are not as safety-hardened, so it is easier to coax unsafe behaviour out of them, which is a PR risk. - It may be possible to divulge proprietary secrets from the model…

> It is trivial to extract samples of the training data that was used, which can bolster existing lawsuits/foster new ones.

At least to this point, the legal teams could get the model via discovery. IDK that the lawfirms realize that they could get experts (or that they'd have contacts that could) to search the model weights.

Re: GLM-5.3 is now open-weight

#202

Post by zackify »

jaggederest wrote: post #193
rkangel wrote: post #75

Earlier quoted context omitted.

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 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.

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

Re: GLM-5.3 is now open-weight

#203

Post by Aurornis »

jaggederest wrote: post #193
rkangel wrote: post #75

Earlier quoted context omitted.

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 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.

Re: GLM-5.3 is now open-weight

#204

Post by gpm »

scosman wrote: post #14
JoeLee1991 wrote: post #10

Earlier quoted context omitted.

I've been using it quite a bit too. My main complaint is that it can be really slow sometimes — like, really slow — and the speed feels pretty inconsistent.

z.ai is using all Chinese hardware for flash: https://thenewstack.io/glm-5-3-flash-chinese-chips/ There are other providers with much faster inference, like BaseTen at >100t/s: https://openrouter.ai/z-ai/glm-5.3-flash#performance

Does Chinese hardware mean fabbed in China or designed in China and fabbed by TSMC?

Re: GLM-5.3 is now open-weight

#205

Post by copperx »

victords wrote: post #151
frigidwalnut wrote: post #113

Earlier quoted context omitted.

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.

Re: GLM-5.3 is now open-weight

#207

Post by everforward »

r_lee wrote: post #90
everforward wrote: post #30

Earlier quoted context omitted.

Sort of depends on how well the core reasoning works. It’s not a big effort to connect an LLM to a search provider. You do pay for the tokens, but in theory on a smaller model each token is cheaper.

honestly using search isn't that great, you mostly get SEO slop, it usually won't help the model ask the right questions

When I messed with it I used Kagi's search and I didn't have that issue (not claiming they're the best, they're the only one I tried).

They filter their results through their AI, though, so you get a sort of meta-summary of the top few results. It did well with geopolitical news stuff, but I've not tried a hard science sort of query.

Re: GLM-5.3 is now open-weight

#208

Post by jaggederest »

zackify wrote: post #202
jaggederest wrote: post #193

Earlier quoted context omitted.

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.

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?

Re: GLM-5.3 is now open-weight

#209

Post by jaggederest »

Aurornis wrote: post #203
jaggederest wrote: post #193

Earlier quoted context omitted.

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

Re: GLM-5.3 is now open-weight

#210

Post by jaggederest »

jaggederest wrote: post #209
Aurornis wrote: post #203

Earlier quoted context omitted.

> 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…

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".
Post reply on HN