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

61–70 of 296 posts

Re: GLM-5.3 is now open-weight

#61

Post by Philpax »

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 (e.g. architectural details that may still be relevant).

For these reasons, and more, it's unlikely that GPT-3/similar models will be released until these concerns are no longer relevant (e.g. when they become a purely historic concern, similar to the open-sourcing of other proprietary software from decades ago).

Re: GLM-5.3 is now open-weight

#62

Post by villish »

mmastrac wrote: post #31

I previously posted that DS4Flash was _good_ but not _great_ on two DGX Sparks, but I have to say that GLM-5.3 is pretty amazing. It's been able to tackle all the random hard problems I've thrown at it and it has the intuition that DS4Flash seems to lack. We're nowhere near a Fable-class model IMO, but things are going to get interesting in this next year.

What quant are you running and tps?

Re: GLM-5.3 is now open-weight

#63

Post by stavros »

fra wrote: post #11

h/t to DeepInfra for being the first 3rd party provider for it on OpenRouter ( https://openrouter.ai/z-ai/glm-5.3?endpoint=b711bea7-3994-49... ).

Have you guys been having a good experience with OpenRouter? I tried it out recently with Claude, and it cached no tokens, charging me $200 for one conversation of 11 messages.

Re: GLM-5.3 is now open-weight

#65

Post by Der_Einzige »

revolvingthrow wrote: post #16

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…

[flagged]

Re: GLM-5.3 is now open-weight

#66

Post by xscott »

gruez wrote: post #35
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?

>but what is his reasoning for not publishing it now, in 2026? What's the point of publishing it when it'll likely be outclassed by gpt-oss?

Maybe I'm reading too much between the lines, but I suspect the reason is to rub his nose in the duplicity or naivety depending on how generous you're feeling. Publishing the model would be a confession that he was wrong.

AI policy is being shaped somewhat by the things Sam and Dario say. So even if you're not feeling vindictive, it's probably good to keep a track record of the previous things they have said as a Bayesian prior. People who don't know better listen to these people, and maybe they shouldn't.

Re: GLM-5.3 is now open-weight

#67

Post by nazgulsenpai »

lnenad wrote: post #43
revolvingthrow wrote: post #16

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…

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.

Curious about that price, if you don't mind sharing a ballpark

Re: GLM-5.3 is now open-weight

#68

Post by peri-cl »

walrus01 wrote: post #20
revolvingthrow wrote: post #16

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…

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?

Re: GLM-5.3 is now open-weight

#70

Post by jchw »

Philpax wrote: post #53
jchw wrote: post #51

Earlier quoted context omitted.

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.

Post reply on HN