Qwen 3.6 27B is the sweet spot for local development
Qwen 3.6 27B is finally a smart model we can use for coding on Macbook or Nvidia RTX - with llama.cpp and OpenCode.
Piotr Migdał
Read more
Optimize your AI costs
Full quality, fewer tokens.
We find what burns your team's AI budget and fix it.
Let's talkBook a direct call with the CEOObserve
Where every token goes: by model, team, and use case.
Organize
Budgets and limits per team. No end-of-month surprises.
Optimize
Right-size models, tighten prompts, cut context. Evals keep quality in check.
Latest insights
Explore our research on AI agents, benchmarking, and evaluation
Compare harnesses not models: Blitzy vs GPT-5.4 on SWE-Bench Pro
An independent audit of agentic scaffolding and harnesses. We analyze how agent workflows, codebase documentation, and test verification impact performance compared to raw base models like GPT-5.4, Gemini 3.1 Pro, and Claude Code.
Piotr Migdał & Piotr Grabowski
Read more
Reviving a 20-year-old puzzle game Chromatron with Ghidra and AI
Decompiling the classic puzzle game with lasers Chromatron from WinXP and PowerPC executables into Rust. A pixel-perfect porting using Claude Code, Opus 4.6, Cursor, GPT-5.2-Codex, and Ghidra.
Piotr Migdał
Read more