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

GLM 5.2 beats Claude in our benchmarks

semgrep.dev

Post reply on HN
Print view View original

61–70 of 559 posts

Re: GLM 5.2 beats Claude in our benchmarks

#61

Post by dakolli »

8note wrote: post #58
dakolli wrote: post #55

Earlier quoted context omitted.

8 X RTX6000. It will run you around 80-100k to get started with a model at this size with decent tps.. Don't worry though, open source evangelists will tell you that these will be running on your phone in the next 3 years. For $100k you could run this model 24/7 through open router with 10 concurrent sessions at 50tps for a decade and have money left over for a vacation. There's no point in investing this type of mon…

you can however, have fun with it. oil workers buy 100k trucks they do not-much with. why not a 100k in computer?

Sure, If you want to light money on fire for entertainment, more power to you. There's probably worse ways to light 100k on fire. If I have an extra 100k laying around it's going to my family though.

Re: GLM 5.2 beats Claude in our benchmarks

#62

Post by dakolli »

rekttrader wrote: post #60
dakolli wrote: post #55

Earlier quoted context omitted.

8 X RTX6000. It will run you around 80-100k to get started with a model at this size with decent tps.. Don't worry though, open source evangelists will tell you that these will be running on your phone in the next 3 years. For $100k you could run this model 24/7 through open router with 10 concurrent sessions at 50tps for a decade and have money left over for a vacation. There's no point in investing this type of mon…

Or you have data that HIPAA, GDPR, PII, or have to care about the concern of others training on your data.

That too.

Re: GLM 5.2 beats Claude in our benchmarks

#63

Post by Ken_At_EM »

8note wrote: post #58
dakolli wrote: post #55

Earlier quoted context omitted.

8 X RTX6000. It will run you around 80-100k to get started with a model at this size with decent tps.. Don't worry though, open source evangelists will tell you that these will be running on your phone in the next 3 years. For $100k you could run this model 24/7 through open router with 10 concurrent sessions at 50tps for a decade and have money left over for a vacation. There's no point in investing this type of mon…

you can however, have fun with it. oil workers buy 100k trucks they do not-much with. why not a 100k in computer?

I can't help but ask where this comment came from, you must have some exposure..

Re: GLM 5.2 beats Claude in our benchmarks

#64

Post by mkagenius »

mcintyre1994 wrote: post #16
gruez wrote: post #4

Earlier quoted context omitted.

>GLM export controls incoming? US imposing export restrictions on a model from China?

It’d be restrictions on Americans and American companies, and probably also pressure on America’s allies.

Token smuggler sounds like a profession coming soon. For distillation and stuff.

Re: GLM 5.2 beats Claude in our benchmarks

#65

Post by HKCM852 »

pimeys wrote: post #59

I have taken another look on these open models after the fiasco of Fable and GPT 5.6 this weekend and... GLM-5.2 truly is a good workhorse model for daily programming. I consider myself a heavy user of LLMs and a seasoned developer. A typical session for me with GPT is usually over a hundred dollars... This weekend I programmed a matrix bot with encryption and a Rust agent with some tools. Because I need one and Open…

Which harness did u use?

Re: GLM 5.2 beats Claude in our benchmarks

#67

Post by dist-epoch »

pimeys wrote: post #59

I have taken another look on these open models after the fiasco of Fable and GPT 5.6 this weekend and... GLM-5.2 truly is a good workhorse model for daily programming. I consider myself a heavy user of LLMs and a seasoned developer. A typical session for me with GPT is usually over a hundred dollars... This weekend I programmed a matrix bot with encryption and a Rust agent with some tools. Because I need one and Open…

$20 on API pricing or on subscription?

Re: GLM 5.2 beats Claude in our benchmarks

#68

Post by krackers »

dakolli wrote: post #55
bArray wrote: post #37

Apparently GLM 5.2 is 753B parameters [1], what kind of hardware are people using to run this locally? [1] https://huggingface.co/zai-org/GLM-5.2

8 X RTX6000. It will run you around 80-100k to get started with a model at this size with decent tps.. Don't worry though, open source evangelists will tell you that these will be running on your phone in the next 3 years. For $100k you could run this model 24/7 through open router with 10 concurrent sessions at 50tps for a decade and have money left over for a vacation. There's no point in investing this type of mon…

Would you be better off pooling that money with some hackerspace group and then setting up shared inference infra, so that way you at least get better utilization?

Re: GLM 5.2 beats Claude in our benchmarks

#69

Post by shostack »

pimeys wrote: post #59

I have taken another look on these open models after the fiasco of Fable and GPT 5.6 this weekend and... GLM-5.2 truly is a good workhorse model for daily programming. I consider myself a heavy user of LLMs and a seasoned developer. A typical session for me with GPT is usually over a hundred dollars... This weekend I programmed a matrix bot with encryption and a Rust agent with some tools. Because I need one and Open…

If you're using Matrix, consider Hermes as a harness if you haven't already. Native gateway support. I've been primarily using mine through Element and it has largely been great.
Post reply on HN