Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Model is suspiciously fast and has a low reported output token count (using via OpenRouter's Chat), both of which aren't representative of models from the big Chinese labs. Odd.


> Model is suspiciously fast

> aren't representative of models from the big Chinese labs

There were reports that China has let Nvidia's chips through, so this might be it. Testing both the chip and infrastructure.


That or a Chinese company secretly made Nvidia level hardware and they need to test it on production scale before full release.


GLM-5.3 is one of the faster models, at least according to artificialanalysis - openAI and Anthropic are the slowest.


Glm-5.3 is dog slow compared to opus and sol. I tried the same real world task on all three and GLM-5.3 was the slowest by a factor of 3.


On their API? Almost definitely, China is good GPU constrained. On the technical aspects? Absolutely not, GLM 5.3 is a relatively small MoE.


On matched hardware?


i'm pretty sure they mean on their official APIs? how would they know what hardware anthropic and openai run their models on?


> suspiciously fast

They're reporting ~30tps, that's about in line with many medium sized models served by Chinese providers




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: