if you are running bonsai 2 on a 3060 or any other card and it comes back with nothing,…
This is a dev post classified by Jev as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
if you are running bonsai 2 on a 3060 or any other card and it comes back with nothing, you are missing a flag. the template defaults reasoning_effort to xhigh, which tells the model to think carefully before it answers, so i tested what that costs. three build tasks, two output limits, two settings, two runs each, greedy, every pair identical. on my 3060 with a 4k output limit all three came back empty, 108 seconds of thinking each and zero tokens of answer. four times the limit saved two of them at six minutes apiece, and the svg was still empty at 477 seconds. flag is simple, --reasoning
Posted by Sudo su (36.4k followers) 16 h ago · 68 likes · 5.1k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: ternary-bonsai-2-27b-ptq1_0-mtp-gguf.
More dev work like this
- The Dot platform has processed 6.18B tokens this week, representing 34.33% of our… — @usedotai
- What is Jev, the tool buzzing across Silicon Valley lately? — @hayden090807
- PSA - Claude code: Turn off the prompt suggestions, save ~10% of your limits/spend — @akshdeeps_001
- 智谱 GLM Coding Plan 开启中秋加国庆双节畅享活动。 — @0xLogicrw
- 😱 什么？！仅 0.6B 本地开源决策模型在 Typed Decisions 上压过 Laya ！ — @NFT_Chen
- Runs the 2.78-trillion-parameter Kimi K3 model on a single CPU using 8 GB of RAM without… — @tom_doerr
- CLAUDE.md 里写了一堆规则，Claude Code 照样有一半当没看见，这事很多人都碰到过。 — @GitHub_Daily
- 🤯卧槽！开源圈又杀出个比 Laya 更狠的 System-1 决策核模型 AgentJev-0.6B ！ — @NFT_Chen
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 20.7k posts from 4.9k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 08:21 UTC. Full method.