[flagged]
Show HN: Getting GLM 5.2 running on my slow computer
261–269 of 269 posts
Re: Show HN: Getting GLM 5.2 running on my slow computer
#262I am curious if it's possible to use coli on ubuntu as coding agent, as i've got a machine with 32GB RAM and 2T SSD.
Re: Show HN: Getting GLM 5.2 running on my slow computer
#263I am curious if it's possible to use coli on ubuntu as coding agent, as i've got a machine with 32GB RAM and 2T SSD.
13th Gen Intel® Core™ i7-1360P × 16
Re: Show HN: Getting GLM 5.2 running on my slow computer
#264I only have 16GB of RAM in my laptop, but I would love to run a powerful model like that even at 0.5 tokens/s. For the questions I am asking, such a speed is more than enough. If anyone has any suggestions, please let me know! I am not an expert on LLMs, just a humble mathematician.
Someone posted this fork, which should work in just 10 GB RAM, at least for another big model. I thought of your request and came back to spread the news :)
Re: Show HN: Getting GLM 5.2 running on my slow computer
#265any one have experience or comments on coli with glm5.2 vs codex with gpt5.4mini
Re: Show HN: Getting GLM 5.2 running on my slow computer
#266Pretty cool! I've also been playing around with GLM 5.2 this week and was equally impressed. At work we're running it locally on some crazy expensive hardware as a test before starting another project so it's great to see people taking this massive FOSS model release and running it on an average machine, even if it's not terribly practical at this point. Nice work!
which hardware?
8 Nvidia B200s. Crazy from an individual perspective, costly for a small business!
Re: Show HN: Getting GLM 5.2 running on my slow computer
#267Earlier quoted context omitted.
Yeah, I really should know. But I'm using whatever ollama gave me by default, which probably isn't optimal.
Ollama uses 4 bit quants and a very short context window by default. It can easily break on anything more complex than a simple chat.
Oh, the context window I overrode immediately, the default one can't even reach my prompt in opencode, it's pushed out by all the pre- and post-amble. But I should probably try something less compressed next time I bother.
Re: Show HN: Getting GLM 5.2 running on my slow computer
#268has anyone tried hosting this on a machine that's not a laptop like a EC2? Curious if we can get better performance than on bedrock (which does not yet support GLM 5.2)
Re: Show HN: Getting GLM 5.2 running on my slow computer
#269I only have 16GB of RAM in my laptop, but I would love to run a powerful model like that even at 0.5 tokens/s. For the questions I am asking, such a speed is more than enough. If anyone has any suggestions, please let me know! I am not an expert on LLMs, just a humble mathematician.
Someone posted this fork, which should work in just 10 GB RAM, at least for another big model. I thought of your request and came back to spread the news :) https://github.com/ErikTromp/colibri-hy3
Thank you very much!