You’re right about the coding, but not about the rest. I use this 27B for everyday tasks that aren’t actually coding. When it comes to coding, GLM5.2 is, in my view, a marvel; it’s inexpensive and works very well when used properly – but for everything else, from sorting emails to pre-generation and analysis of varying quality, it does the job that GPT and Claude can’t do for free, and sometimes not quite as well. I use Claude for coding because I’ve got used to the way it works, which suits me. But the 27B does the opposite: the ‘local’ mode is there to help you get used to the way it works, and that might be the point.
HN user
edyos
2 karma
Posts1
Comments3
No, Qwen 27B isn't the sweet spot 13 days ago
They play the game of China, they are stupid. US, as EU, lost everything with this stupid posture.
Author here. VarLiNGAM is the reference algorithm for causal discovery in time series. The Python implementation doesn't scale past ~10 variables. I rewrote it from scratch in pure Rust.
Results: 14-50x faster, 3-6x less memory, <1% precision gap vs ground truth. Drop-in replacement via PyO3.
Happy to answer questions about the implementation choices.