Sebastian Raschka, PhD, is an LLM Research Engineer and AI expert bridging academia and industry, specializing in large language models, high-performance AI systems, and practical, code-driven machine learning.
122 articles from this blog
Overview of recent notable open-weight AI model releases, including Nanbeige, Laguna, Motif, Solar Open, and Antares.
Thanks everyone for all the kind words and feedback. Super happy that you are enjoying Build a Reasoning Model (From Scratch)! Unfortunately, there’s
Explains how LLMs learn low, medium, and high-effort reasoning modes, covering training techniques and effort settings.
Analysis of Thinking Machines Lab's new open-weight 975B MoE LLM, Inkling, including benchmarks, architecture details, and comparisons.
Analysis of GPT 5.6's 72 configurations, mapping model choices and reasoning effort to performance and cost.
Announcement of the release of 'Build a Reasoning Model (From Scratch)', a book on implementing modern AI reasoning techniques.
Tutorial on setting up a local coding agent using open-weight LLMs and open-source tools as an alternative to Claude Code and Codex.
Testing local open-weight LLMs like Qwen-Code and Codex in coding harnesses, comparing token efficiency and performance.
Analysis of GLM-5.2 open-weight model with IndexShare for efficient long-context sparse attention.
Analysis of VibeThinker-3B, a small AI model achieving strong coding and reasoning results through post-training on Qwen2.5-Coder-3B.
Cohere's North Mini Code is a 30B-parameter open-weight model for agentic coding, featuring Mixture-of-Experts architecture and strong benchmark performance.
A curated list of LLM research papers from January to May 2026, covering architecture, reasoning, agents, and more.
Analysis of Nemotron 3 Ultra LLM with Latent MoE scaling, hybrid Mamba-Transformer architecture, and performance benchmarks.
Analysis of MiniMax M2 LLM technical report highlighting production-oriented design choices like full attention, fine-grained MoE, and agent training pipelines.
Explains DeepSeek Sparse Attention implementation from scratch, replacing fixed sparse patterns with learned ones using a lightweight indexer.
Explores recent LLM architecture innovations like KV sharing, compressed attention, and mHC for long-context efficiency.
A talk on implementing LLM architectures from scratch in Python and PyTorch, focusing on tracing design changes in open-weight models.
A workflow for understanding new open-weight LLM architectures using config files and code from Hugging Face.
An overview of coding agent components, including tools, memory, and repo context, to enhance LLM performance in software development.
Analysis of Gemma 4 31B architecture, benchmarks, and comparison with prior models like Gemma 3 and Qwen3.5.
