
A 27B Model in 6GB, and Cutting Agent Tokens | 05 Oct 26
Ternary Bonsai 2 squeezes a 27B Qwen model to under 6GB, Headroom compresses what your agent reads before the model sees it, Codex CLI 0.160 ships, and Pi 1.0 and DeepSeek Harness join the agent harness race. Today we teach quantization and what an agent harness is. Hosts: Alex & Jules. New episodes daily.
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.