LLMs from Scratch vs 
Made With ML
LLMs from Scratch vs Made With ML compared for 2026 — features, license, ease of use, performance and which one to choose. Build a GPT from nothing, line by line vs From notebook to production system.
Updated regularly · curated by OpenSourceAI.tech
LLMs from Scratch vs Made With ML at a glance
| Spec | LLMs from Scratch | Made With ML |
|---|---|---|
| Category | Learn AI & machine learning | Learn AI & machine learning |
| Type | Book + code | Course (MLOps) |
| License | Apache-2.0 | MIT |
| Runs locally | Yes | Yes |
| Primary language | Python | Python |
| Ease of use | Intermediate | Intermediate |
| Best for | genuinely understanding how an LLM works | the gap between a notebook and production |
| GitHub stars | 99k | 48.7k |
How LLMs from Scratch and Made With ML score
| Criterion | LLMs from Scratch | Made With ML |
|---|---|---|
| Popularity | 4.5 | 4.0 |
| Maintenance | 5.0 | 4.0 |
| 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
Made With ML
Goku Mohandas' course on taking ML from a notebook to a reliable production system: testing, CI/CD, monitoring, and the engineering most courses ignore.
- Covers the engineering that courses skip
- Testing, CI/CD and monitoring for ML
- Written by a practitioner, not an academic
Key differences
LLMs from Scratch is book + code, while Made With ML is course (MLOps). 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 Made With ML fits the gap between a notebook and production.
Which should you choose?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose Made With ML for the gap between a notebook and production.
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 Made With 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 Made With ML free?
LLMs from Scratch is free and open source (Apache-2.0), and Made With ML is free and open source (MIT). Neither charges for the core software.
Can I run LLMs from Scratch and Made With ML locally?
LLMs from Scratch: yes · Made With ML: yes. Both can be used without sending your data to a third-party cloud where their setup allows.
LLMs from Scratch vs Made With ML — which should I pick in 2026?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose Made With ML for the gap between a notebook and production.
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 →