Testing small models for personal agent efficacy is fun- especially when you're doing it…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Testing small models for personal agent efficacy is fun- especially when you're doing it on hardware that was never designed for local LLMs (M2 MacBook Air). This is MiniCPM5-2B making short work of a universe of personal context data, executing tool calls and agent loops to give me the insights I need. Looking at it from the backend logging in LM Studio:
Posted by GooGZ AI (1.4k followers) 1 h ago · 5 likes · 395 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Claude Code does not need unlimited memory to retain useful project context. Give it a… — @catmanyau
- Jev and LLMs: who does what? — @bibryam
- there's no way Ado will answer in the replies but it would be funny if she did — @secemp9
- Jev Founder, Diogo Amogo, just released a PDF on building a Jev Harness for coding agents — @zodchiii
- made a @ado1024imokenp 's codex pet for the @OpenAI codex desktop app… — @secemp9
- Your agent’s memory shouldn’t disappear when a session ends. — @DanKornas
- I used to be scared of VFX. Now I'm bringing my ideas to life with GPT-6. — @Stefan_3D_AI
- https://github.com/ddalcu/mlx-serve/releases/tag/v26.9.5 — @ddalcu
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. 20.9k posts from 5k 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 13:11 UTC. Full method.