LLMs from Scratch vs 
Neural Networks: Zero to Hero
LLMs from Scratch vs Neural Networks: Zero to Hero compared for 2026 — features, license, ease of use, performance and which one to choose. Build a GPT from nothing, line by line vs Karpathy builds backprop, then GPT, from scratch.
Updated regularly · curated by OpenSourceAI.tech
LLMs from Scratch vs Neural Networks: Zero to Hero at a glance
| Spec | LLMs from Scratch | Neural Networks: Zero to Hero |
|---|---|---|
| Category | Learn AI & machine learning | Learn AI & machine learning |
| Type | Book + code | Video course + code |
| License | Apache-2.0 | MIT |
| Runs locally | Yes | Yes |
| Primary language | Python | Jupyter |
| Ease of use | Intermediate | Intermediate |
| Best for | genuinely understanding how an LLM works | the single best way to truly understand deep learning |
| GitHub stars | 99k | — |
How LLMs from Scratch and Neural Networks: Zero to Hero score
| Criterion | LLMs from Scratch | Neural Networks: Zero to Hero |
|---|---|---|
| Popularity | 4.5 | n/a |
| Maintenance | 5.0 | n/a |
| 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
Neural Networks: Zero to Hero
Andrej Karpathy's legendary lecture series: you build automatic differentiation, then a language model, then GPT — writing every line yourself, with nothing hidden.
- Widely considered the best deep learning teaching ever made
- You implement backpropagation yourself — it finally clicks
- Ends with a working GPT you wrote line by line
Key differences
LLMs from Scratch is book + code, while Neural Networks: Zero to Hero is video course + code. 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 Neural Networks: Zero to Hero fits the single best way to truly understand deep learning.
Which should you choose?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose Neural Networks: Zero to Hero for the single best way to truly understand deep learning.
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 Neural Networks: Zero to Hero 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 Neural Networks: Zero to Hero free?
LLMs from Scratch is free and open source (Apache-2.0), and Neural Networks: Zero to Hero is free and open source (MIT). Neither charges for the core software.
Can I run LLMs from Scratch and Neural Networks: Zero to Hero locally?
LLMs from Scratch: yes · Neural Networks: Zero to Hero: yes. Both can be used without sending your data to a third-party cloud where their setup allows.
LLMs from Scratch vs Neural Networks: Zero to Hero — which should I pick in 2026?
Choose LLMs from Scratch for genuinely understanding how an LLM works. Choose Neural Networks: Zero to Hero for the single best way to truly understand deep learning.
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 →