Build a Reasoning Model From Scratch Is Out

Sebastian Raschka announced the release of his new book "Build a Reasoning Model (From Scratch)", a 440-page full-color guide that teaches readers how to implement modern reasoning techniques on a Qwen3 base model. The book covers inference scaling, reinforcement learning, and distillation, and is now shipping from Manning Publications with Amazon preorders available.

Build a Reasoning Model From Scratch Is Out A year and a half, countless experiments, and hundreds of pages later… today was one of my favorite days as an engineer and author. Build a Reasoning Model From Scratch is finally out, and my first copies just arrived 440 full-color pages. A huge thank you to everyone who joined me as an early reader and reviewer over the past 1.5 years. I hope this is a worthy sequel to Build a Large Language Model From Scratch . If you are wondering what it covers, it walks you through implementing modern reasoning techniques from scratch on top of a small Qwen3 base model /glossary/ base-model , with a focus on: - inference scaling - reinforcement learning distillation /glossary/ distillation While Build a Large Language Model From Scratch focuses on building and pre-training an LLM, this book picks up where that one leaves off and covers what comes next. If you enjoy model architecture details, don’t worry, the complete Qwen3 architecture is also implemented from scratch and explained in the appendix. The book is now shipping from the publisher: Build a Reasoning Model From Scratch https://mng.bz/Nwr7 And it is also available for preorder on Amazon. Shipping is expected to begin there in a few weeks: Amazon preorder for Build a Reasoning Model From Scratch https://amzn.to/4aAKiFY I hope it serves as a useful resource for anyone who wants to understand how reasoning models, which are now a key component of many modern AI agents, work under the hood. Thanks again to everyone who helped make this book possible Happy reading Source: lightly edited website version of my Substack note https://substack.com/@rasbt/note/c-285445410 . Read Next Inkling: A New Open-Weight 975B MoE with a Few Surprises Short note on Thinking Machines Lab's 975B Inkling open-weight model, its benchmark profile, sparse MoE design, short convolutions, embedding RMSNorm, and /blog/2026/inkling-architecture-benchmark-notes.html 200,000 Subscribers Short note celebrating Ahead of AI reaching 200,000 subscribers. /blog/2026/ahead-of-ai-reached-200000-subscribers.html GPT 5.6 Has 72 Possible Configurations. What's A Good Default? Short note on how GPT 5.6 model and effort choices map onto training-time and inference-time scaling, producing 72 configurations. /blog/2026/gpt-5-6-configurations.html