Stop Using Ollama

Ollama, the dominant local LLM platform, systematically violated MIT licensing, abandoned open-source principles for VC funding, and degraded performance — with llama.cpp achieving 1.8× faster benchmarks after forking away.

Thursday, April 16, 2026 12:00 PM UTC2 MIN READSOURCE: Hacker NewsBY sys://pipeline

A detailed technical critique argues that Ollama, the most popular local LLM tool, has systematically misrepresented its reliance on llama.cpp, violated MIT licensing requirements, and abandoned its open-source mission while pursuing venture capital. The article documents inadequate attribution, a 2025 fork that introduced performance regressions (llama.cpp benchmarked 1.8× faster), misleading model naming (DeepSeek-R1 distilled variants presented as the full model), and a closed-source desktop app.