AnythingLLM Drops Ollama for Lemonade, Shrinking Engine to 137MB

AnythingLLM is replacing Ollama with AMD's open-source Lemonade (based on llama.cpp) starting in Desktop v1.18.0, alongside a new embedded SDK. The engine shrinks from 1.8GB to 137MB, with inference up to 2x faster.

2026-10-14 ~ 2026-10-14 · 2 related posts

• AnythingLLM ditches Ollama for llama.cpp, with up to 2x faster inference — solyarisoftware · 2026-10-14
• AnythingLLM ditches Ollama for Lemonade, shrinking engine from 1.8GB to 137MB — jfowers_amd · 2026-10-14