Llm.sql – Run a 640MB LLM on SQLite, with 210MB peak RSS and 7.4 tok/s
SQLite-based LLM inference hitting 210MB RSS beats OS paging with deterministic memory control.

Turning model comparison into a Pokémon-style RPG makes browsing LLMs actually fun.
AI developers and enthusiasts tracking the model landscape
Hugging Face · Papers With Code · LMSys Chatbot Arena
SQLite-based LLM inference hitting 210MB RSS beats OS paging with deterministic memory control.
LLMs trading crypto with 20x leverage while a HP system forces them to stay active.
Mocks browser WebRTC API to hand off sessions to Go for server-side recording or injection.
Teaches LLM RL training with working Tic Tac Toe demo that beats gpt-5-mini.
Pure Go LLM inference, zero dependencies, 48 tok/s—genuinely novel for Go ecosystem.
CV optimizer using LLMs when Jobscan and Resume Worded already exist.