LLMs from Scratch vs 
Applied ML
LLMs from Scratch vs Applied ML compared for 2026 — features, license, ease of use, performance and which one to choose. Build a GPT from nothing, line by line vs How real companies actually ship ML.
Updated regularly · curated by OpenSourceAI.tech
LLMs from Scratch vs Applied ML at a glance
| Spec | LLMs from Scratch | Applied ML |
|---|---|---|
| Category | Learn AI & machine learning | Learn AI & machine learning |
| Type | Book + code | Curated papers & posts |
| License | Apache-2.0 | MIT |
| Runs locally | Yes | Yes |
| Primary language | Python | Markdown |
| Ease of use | Intermediate | Intermediate |
| Best for | genuinely understanding how an LLM works | learning from what companies really did |
| GitHub stars | 99k | 29.9k |
How LLMs from Scratch and Applied ML score
| Criterion | LLMs from Scratch | Applied ML |
|---|---|---|
| Popularity | 4.5 | 3.5 |
| Maintenance | 5.0 | 2.0 |
| Ease of use | 3.5 | 3.5 |
| Privacy | 5.0 | 5.0 |
| License freedom | 5.0 | 5.0 |
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
Applied ML
Eugene Yan's curated collection of papers and engineering blog posts on how companies actually build and deploy ML systems in production — organised by problem, not by algorithm.
- Real production systems, not toy examples
- Organised by problem, not by algorithm
- Curated by a practising ML engineer
Key differences
LLMs from Scratch is book + code, while Applied ML is curated papers & posts. Their licenses differ (Apache-2.0 vs MIT), which matters if you ship a commercial product. In short, LLMs from Scratch fits genuinely understanding how an LLM works, and Applied ML fits learning from what companies really did.
Which should you choose?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose Applied ML for learning from what companies really did.
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 Applied ML easier to use?
Both sit at a similar level (Intermediate). Your choice should come down to fit rather than difficulty.
Are LLMs from Scratch and Applied ML free?
LLMs from Scratch is free and open source (Apache-2.0), and Applied ML is free and open source (MIT). Neither charges for the core software.
Can I run LLMs from Scratch and Applied ML locally?
LLMs from Scratch: yes · Applied ML: yes. Both can be used without sending your data to a third-party cloud where their setup allows.
LLMs from Scratch vs Applied ML — which should I pick in 2026?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose Applied ML for learning from what companies really did.
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 →