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

GLM-5.3-Flash

z.ai

Post reply on HN
Print view View original

11–20 of 605 posts

Re: GLM-5.3-Flash

#13

Post by kilroy123 »

mmastrac wrote: post #7

Weights on HF here: https://huggingface.co/zai-org/GLM-5.3-Flash I decided to take the plunge and get myself four sparks at a decent price (and bought the QSFP cables from AliExpress because they are literally 1/2 the price of Amazon), even knowing Apple was going to release new hardware and there's probably a spark 2 on the horizon. It looks like this is going to be a decent fit for what I need. I've been experiment…

> get myself four sparks at a decent price

Wow, if you don't mind me asking. How and where?

Re: GLM-5.3-Flash

#14

Post by Bluestein »

sunbum wrote: post #5

> with all of this traffic served on Chinese AI chips RIP Nivida shareholders

This is the takeaway here: That's how they have been serving it at scale as Ox-Alpha. This is a definitional moment.-

Further quote:

"Compared with our initial baseline on the same hardware, we achieved a 3× improvement in end-to-end serving performance, reaching hardware efficiency and per-token cost comparable to mainstream NVIDIA GPUs. This demonstrates that Chinese chips can support frontier-model inference efficiently and economically at scale."

https://z.ai/blog/glm-5.3-flash

Re: GLM-5.3-Flash

#16

Post by TaLiTr »

> it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks.

From a biased source, but would be big if true. I've had great results with GLM 5.2.

From their subscription page, the smallest plan gives you about 97M tokens weekly for 5.3 but 292M for 5.3 Flash. Not exactly 10x the limit.

Re: GLM-5.3-Flash

#17

Post by mmastrac »

kilroy123 wrote: post #13
mmastrac wrote: post #7

Weights on HF here: https://huggingface.co/zai-org/GLM-5.3-Flash I decided to take the plunge and get myself four sparks at a decent price (and bought the QSFP cables from AliExpress because they are literally 1/2 the price of Amazon), even knowing Apple was going to release new hardware and there's probably a spark 2 on the horizon. It looks like this is going to be a decent fit for what I need. I've been experiment…

> get myself four sparks at a decent price Wow, if you don't mind me asking. How and where?

I bought 4x Asus GX10 with the 1TB option. I don't understand why, but it's the only model in the whole lineup that isn't priced insanely.

They were briefly on sale with a $200-off coupon, but they show up on warehouse deals from time-to-time as well.

Re: GLM-5.3-Flash

#18

Post by colingauvin »

revolvingthrow wrote: post #10

> 320B total parameters and just 18B active parameters This is pretty hefty for a "flash" model, even a 256 GB setup is insufficient at q4 - and q4 is already the worst-but-still-acceptable quant in my experience. The benchmarks look great, especially since GLM tends to be more honest than the average Chinese lab, but you’ll need to splurge to run it at home. @edit: so many releases that I forgot to math. This fits j…

That's 160GB-ish for Q4...how is 256 insufficient?

Re: GLM-5.3-Flash

#19

Post by javier123454321 »

Xunjin wrote: post #8
iamsyr wrote: post #3

Standard API Pricing for GLM-5.3-Flash (per 1M tokens) - Input: $0.15 - Output: $0.50 - Cached input: $0.03

Is that cheaper than DS4 flash?

All I can say is that even if it is, I was almost glad to go back to using DS4 Flash. Because 0XAlpha was just so friggin slow to complete a task because of the level of circular reasoning that it would go over and over into, sometimes even returning no output. If I just wanted something done I would switch from a free model to a paid one which is crazy.
Post reply on HN