Comments here seem to be talking like they've used this model for longer than a few hours -- is this true, or are y'all just sharing your initial thoughts?
GLM-5.1: Towards Long-Horizon Tasks
41–50 of 285 posts
Re: GLM-5.1: Towards Long-Horizon Tasks
#42I find the "8 hour Linux Desktop" bit disingenuous, in the fine print it's a browser page:
> "build a Linux-style desktop environment as a web application"
We all know that building a spec-compliant browser alone is a herculean task.
Re: GLM-5.1: Towards Long-Horizon Tasks
#43I am on their "Coding Lite" plan, which I got a lot of use out of for a few months, but it has been seriously gimped now. Obvious quantization issues, going in circles, flipping from X to !X, injecting chinese characters. It is useless now for any serious coding work.
I'm on their lite plan as well and I've been using it for my OpenClaw. It had some issues but it also one-shotted a very impressive dashboard for my Twitter bookmarks.
For the price this is a pretty damn impressive model.
Re: GLM-5.1: Towards Long-Horizon Tasks
#44To be honest I am a bit sad as, glm5.1 is producing mich better typescript than opus or codex imo, but no matter what it does sometimes go into shizo mode at some point over longer contexts. Not always tho I have had multiple session go over 200k and be fine.
After the context gets to 100k tokens you should open a new session or run /compact.
Re: GLM-5.1: Towards Long-Horizon Tasks
#45Unsloth quantizations are available on release as well. [0] The IQ4_XS is a massive 361 GB with the 754B parameters. This is definitely a model your average local LLM enthusiast is not going to be able to run even with high end hardware. [0] https://huggingface.co/unsloth/GLM-5.1-GGUF
SSD offload is always a possibility with good software support. Of course you might easily object that the model would not be "running" then, more like crawling. Still you'd be able to execute it locally and get it to respond after some time.
Meanwhile we're even seeing emerging 'engram' and 'inner-layer embedding parameters' techniques where the possibility of SSD offload is planned for in advance when developing the architecture.
Re: GLM-5.1: Towards Long-Horizon Tasks
#46To be honest I am a bit sad as, glm5.1 is producing mich better typescript than opus or codex imo, but no matter what it does sometimes go into shizo mode at some point over longer contexts. Not always tho I have had multiple session go over 200k and be fine.
When it works and its not slow it can impress. Like yesterday it solved something that kimi k2.5 could not. and kimi was best open source model for me. But it still slow sometimes. I have z.ai and kimi subscription when i run out of tokens for claude (max) and codex(plus).
i have a feeling its nearing opus 4.5 level if they could fix it getting crazy after like 100k tokens.
Re: GLM-5.1: Towards Long-Horizon Tasks
#47How does it compare to Kimi 2.5 or Qwen 3.6 Plus?
Compared to Kimi 2.5 or Qwen 3.6 Plus I don't know, but I ran GLM 5 (not 5.1) side by side with Qwen 3.5 Plus and it was visibly better.
Re: GLM-5.1: Towards Long-Horizon Tasks
#48GLM-5.0 is the real deal as far as open source models go. In our internal benchmarks it consistently outperforms other open source models, and was on par with things like GPT-5.2. Note that we don't use it for coding - we use it for more fuzzy tasks.
Re: GLM-5.1: Towards Long-Horizon Tasks
#49How does it compare to Kimi 2.5 or Qwen 3.6 Plus?
The blog post has a benchmark comparison table with these two in it
Re: GLM-5.1: Towards Long-Horizon Tasks
#50Comments here seem to be talking like they've used this model for longer than a few hours -- is this true, or are y'all just sharing your initial thoughts?
It's been out for a while.