GLM-5.2: Frontier Intelligence, Open Weights

GLM-5.2: Frontier Intelligence, Open Weights(twitter.com)

15 points by zixuanlimit 4 hours ago | 5 comments

osti 3 hours ago |

Given that DeepSwe is one of the very few coding benchmarks worth taking a look at, this achieves rather excellent result at it (not far from opus 4.8).

From looking at the results and my own impression of 5.1 and other models, I think this is the best Chinese coding model by some non-insignificant margin.

LaurensBER 3 hours ago | |

I've been very pleased with it's performance over the last few days.

It's definitely not near Opus 4.8 level but it's very impressive nonetheless and it does do design extremely well.

ebbi 2 hours ago | | |

> it does do design extremely well

Better than Opus?

hadik 3 hours ago |

Blog post with more information including benchmarks: https://z.ai/blog/glm-5.2

dbbk 3 hours ago |

If I have a fully maxed out MacBook Pro, would it make sense to just switch from Opus 4.8 to this? I've never tried running local models for coding...

entrope 1 hour ago | |

HuggingFace says this model has 753B parameters, which will need a lot more RAM than a maxed-out MacBook Pro. With 40B active parameters, running from SSD would need patience.

api 1 hour ago | | |

I’ve wondered for a while if anyone is working on very wide channel parallel (kind of like RAID 0) SSD for this purpose. Couple that with a tensor processor and that would be interesting.

Bucko1 4 hours ago |

I have already tested this and it is impressive.