AI Engineer YouTube · April 29, 2026

Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI

Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI video thumbnail
Why it matters

A new class of small models is emerging with the ability to reliably follow instructions and call tools while running on-device under 1 GB of memory. In this talk, we'll break down how to post-train frontier small models using the LFM2.5 recipe: on-policy preference alignment, agentic reinforcement learning, and curric

My takeaway: A new class of small models is emerging with the ability to reliably follow instructions and call tools while running on-device under 1 GB of memory. In this talk, we'll break down how to post-train frontier small models using the LFM2.5 recipe: on-policy preference alignment, agentic reinforcement learning, and curric