LLMs from Scratch vs 
fastai Book (fastbook)
LLMs from Scratch vs fastai Book (fastbook) compared for 2026 — features, license, ease of use, performance and which one to choose. Build a GPT from nothing, line by line vs Deep learning for coders, top-down.
Updated regularly · curated by OpenSourceAI.tech
LLMs from Scratch vs fastai Book (fastbook) at a glance
| Spec | LLMs from Scratch | fastai Book (fastbook) |
|---|---|---|
| Category | Learn AI & machine learning | Learn AI & machine learning |
| Type | Book + code | Book + course |
| License | Apache-2.0 | Custom (free to read) |
| Runs locally | Yes | Yes |
| Primary language | Python | Jupyter |
| Ease of use | Intermediate | Beginner |
| Best for | genuinely understanding how an LLM works | coders who want results before theory |
| GitHub stars | 99k | 25.1k |
How LLMs from Scratch and fastai Book (fastbook) score
| Criterion | LLMs from Scratch | fastai Book (fastbook) |
|---|---|---|
| Popularity | 4.5 | 3.5 |
| Maintenance | 5.0 | 2.0 |
| Ease of use | 3.5 | 5.0 |
| Privacy | 5.0 | 5.0 |
| License freedom | 5.0 | 3.5 |
Scores are computed automatically from public signals — GitHub stars (popularity), recent commit activity (maintenance), license type (freedom), local-first design (privacy) and onboarding complexity (ease of use). Indicative, not a verdict.
What each one is
LLMs from Scratch
Sebastian Raschka's companion repository to "Build a Large Language Model (From Scratch)": you implement attention, a transformer, pretraining and fine-tuning yourself, in plain PyTorch.
- You build every component yourself — no black boxes
- Runs on a laptop, no cluster needed
- The clearest explanation of attention anywhere
fastai Book (fastbook)
The fast.ai book: teaches deep learning by getting you to a working model in lesson one, then peeling back the layers — the opposite of the usual maths-first approach.
- You train a real model in the first lesson
- Top-down: theory arrives when you need it
- Taught tens of thousands of practitioners
Key differences
LLMs from Scratch is book + code, while fastai Book (fastbook) is book + course. Their licenses differ (Apache-2.0 vs Custom (free to read)), which matters if you ship a commercial product. LLMs from Scratch leans more intermediate-friendly, whereas fastai Book (fastbook) is more suited to beginner users. In short, LLMs from Scratch fits genuinely understanding how an LLM works, and fastai Book (fastbook) fits coders who want results before theory.
Which should you choose?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose fastai Book (fastbook) for coders who want results before theory.
There is rarely one winner — many setups use both. The right pick depends on your hardware, your team's skills, and whether you value simplicity or control.
Frequently asked questions
Is LLMs from Scratch or fastai Book (fastbook) easier to use?
fastai Book (fastbook) is generally the easier of the two to get started with, while LLMs from Scratch rewards more setup with more control.
Are LLMs from Scratch and fastai Book (fastbook) free?
LLMs from Scratch is free and open source (Apache-2.0), and fastai Book (fastbook) is free and open source (Custom (free to read)). Neither charges for the core software.
Can I run LLMs from Scratch and fastai Book (fastbook) locally?
LLMs from Scratch: yes · fastai Book (fastbook): yes. Both can be used without sending your data to a third-party cloud where their setup allows.
LLMs from Scratch vs fastai Book (fastbook) — which should I pick in 2026?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose fastai Book (fastbook) for coders who want results before theory.
People also compare
Explore more open-source AI
Browse thousands of open-source AI tools, models and projects — all curated in one place, updated daily.
Explore the directory →