If you have a 24-64GB mac, consider running Qwen3.8 27B locally at night. It's a bit slower to run locally, but if you're sleeping it's less of a problem.
Depending on your memory, you'll need to use the weaker Q4 versions but they still perform well.
It ranks higher than GPT-5.3 Codex (xhigh) or Claude Opus 4.6 (max) so is great for pairing with <a href="https://github.com/kunchenguid/gnhf" rel="nofollow">https://github.com/kunchenguid/gnhf for nightly experimentation, cleanup, or recommendation lists for in the morning.
You might be interested in <a href="https://prismml.com/news/bonsai-2-27b" rel="nofollow">https://prismml.com/news/bonsai-2-27b
Please cite a reputable source for this claim, and keep in mind we are talking about Bonsai 2 and not the original Bonsai.
Even on the original one, the authors have replied to such issues with working solutions: <a href="https://github.com/PrismML-Eng/Bonsai-demo/issues/131" rel="nofollow">https://github.com/PrismML-Eng/Bonsai-demo/issues/131
Xeoncross · · focus · HN ↗
Depending on your memory, you'll need to use the weaker Q4 versions but they still perform well.
It ranks higher than GPT-5.3 Codex (xhigh) or Claude Opus 4.6 (max) so is great for pairing with <a href="https://github.com/kunchenguid/gnhf" rel="nofollow">https://github.com/kunchenguid/gnhf for nightly experimentation, cleanup, or recommendation lists for in the morning.
ranger_danger · · focus · HN ↗
kolbebe · · focus · HN ↗
ranger_danger · · focus · HN ↗
Even on the original one, the authors have replied to such issues with working solutions: <a href="https://github.com/PrismML-Eng/Bonsai-demo/issues/131" rel="nofollow">https://github.com/PrismML-Eng/Bonsai-demo/issues/131