Comparison
LLMs-from-scratch vs reasoning-from-scratch
Verdict
Pick LLMs-from-scratch if lLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions; pick reasoning-from-scratch if a step-by-step guide to building a reasoning large language model (LLM) using PyTorch, suitable for running on consumer hardware with automatic GPU utilization.
Markdown twin · LLMs-from-scratch alternatives · reasoning-from-scratch alternatives
GraphCanon updated today
vs
Trust & integrity
| Signal | LLMs-from-scratch | reasoning-from-scratch |
|---|---|---|
| Maintenance | Very active (5d since push) As of 2d · github_public_v1 | Active (12d since push) As of today · github_public_v1 |
| Provenance | Not a fork · Personal account As of 2d · github_public_v1 | Not a fork · Personal account As of today · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1mo · osv@v1 | Published findings As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- LLMs-from-scratch
- Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
- reasoning-from-scratch
- Implement a reasoning LLM in PyTorch from scratch, step by step
Stars
- LLMs-from-scratch
- 103k
- reasoning-from-scratch
- 5.0k
Forks
- LLMs-from-scratch
- 16k
- reasoning-from-scratch
- 759
Open issues
- LLMs-from-scratch
- 2
- reasoning-from-scratch
- 2
Language
- LLMs-from-scratch
- Jupyter Notebook
- reasoning-from-scratch
- Jupyter Notebook
Adopt for
- LLMs-from-scratch
- LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions.
- reasoning-from-scratch
- A step-by-step guide to building a reasoning large language model (LLM) using PyTorch, suitable for running on consumer hardware with automatic GPU utilization.
Persona
- LLMs-from-scratch
- -
- reasoning-from-scratch
- -
Runtime
- LLMs-from-scratch
- -
- reasoning-from-scratch
- -
License
- LLMs-from-scratch
- Other
- reasoning-from-scratch
- Apache-2.0 License
Last pushed
- LLMs-from-scratch
- Aug 10, 2026
- reasoning-from-scratch
- Aug 4, 2026
Categories
- LLMs-from-scratch
- LLM Frameworks, Model Training
- reasoning-from-scratch
- LLM Frameworks, Model Training
Trust and health
Maintenance
- LLMs-from-scratch
- Very active (96%)
- reasoning-from-scratch
- Active (82%)
Days since push
- LLMs-from-scratch
- 5d
- reasoning-from-scratch
- 12d
Stars delta
- LLMs-from-scratch
- +3.5k (30d)
- reasoning-from-scratch
- +252 (30d)
Open issues delta
- LLMs-from-scratch
- -1 (30d)
- reasoning-from-scratch
- 0 (30d)
OSV dependency advisories
- LLMs-from-scratch
- No lockfile (source not queried)
- reasoning-from-scratch
- Published findings
Full report
- LLMs-from-scratch
- Trust report
- reasoning-from-scratch
- Trust report
Typed relationship
LLMs-from-scratch alternative reasoning-from-scratchBoth repositories aim to implement a large language model from scratch in PyTorch, but they likely differ slightly in implementation and specifics.
Choose LLMs-from-scratch if…
- License: LLMs-from-scratch is Other, reasoning-from-scratch is Apache-2.0.
- Both repositories aim to implement a large language model from scratch in PyTorch, but they likely differ slightly in implementation and specifics.
- Tags unique to LLMs-from-scratch: attention-mechanism, finetuning, from-scratch, generative-ai.
- - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
When NOT to use LLMs-from-scratch
- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work.
- - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers
- a deeper learning experience.
Choose reasoning-from-scratch if…
- License: reasoning-from-scratch is Apache-2.0, LLMs-from-scratch is Other.
- Requirements: Automatic GPU utilization where available, though not strictly necessary for the early chapters..
- Both repositories aim to implement a large language model from scratch in PyTorch, but they likely differ slightly in implementation and specifics.
- Tags unique to reasoning-from-scratch: chain-of-thought, distillation, inference-time-scaling, large language models.
- When you have intermediate knowledge of PyTorch and want detailed insights into the implementation process of reasoning LLMS.
When NOT to use reasoning-from-scratch
- Avoid this tool if you are looking for rapid prototyping or quick model deployment; it focuses more on understanding and building the LLM from scratch rather than providing prebuilt components.
- If specialized server hardware is available and preferred for the entire project, as chapters 5 and 6 recommend GPU use but earlier sections can be completed with just a CPU.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (rasbt/LLMs-from-scratch) · observed Aug 16, 2026
- GitHub forks (rasbt/LLMs-from-scratch) · observed Aug 16, 2026
- Last push (rasbt/LLMs-from-scratch) · observed Aug 10, 2026
- License file (Other) · observed Aug 16, 2026
- Decision facts (enrichment) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (rasbt/reasoning-from-scratch) · observed Aug 17, 2026
- GitHub forks (rasbt/reasoning-from-scratch) · observed Aug 17, 2026
- Last push (rasbt/reasoning-from-scratch) · observed Aug 4, 2026
- License file (Apache-2.0) · observed Aug 17, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: LLMs-from-scratch 103k · reasoning-from-scratch 5.0k (synced Aug 16, 2026).
Common questions
- What is the difference between LLMs-from-scratch and reasoning-from-scratch?
- LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. reasoning-from-scratch: Implement a reasoning LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories.
- When should I choose LLMs-from-scratch over reasoning-from-scratch?
- Choose LLMs-from-scratch over reasoning-from-scratch when License: LLMs-from-scratch is Other, reasoning-from-scratch is Apache-2.0; Both repositories aim to implement a large language model from scratch in PyTorch, but they likely differ slightly in implementation and specifics; Tags unique to LLMs-from-scratch: attention-mechanism, finetuning, from-scratch, generative-ai; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
- When should I choose reasoning-from-scratch over LLMs-from-scratch?
- Choose reasoning-from-scratch over LLMs-from-scratch when License: reasoning-from-scratch is Apache-2.0, LLMs-from-scratch is Other; Requirements: Automatic GPU utilization where available, though not strictly necessary for the early chapters.; Both repositories aim to implement a large language model from scratch in PyTorch, but they likely differ slightly in implementation and specifics; Tags unique to reasoning-from-scratch: chain-of-thought, distillation, inference-time-scaling, large language models; When you have intermediate knowledge of PyTorch and want detailed insights into the implementation process of reasoning LLMS.
- When should I avoid LLMs-from-scratch?
- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers a deeper learning experience.
- When should I avoid reasoning-from-scratch?
- Avoid this tool if you are looking for rapid prototyping or quick model deployment; it focuses more on understanding and building the LLM from scratch rather than providing prebuilt components. If specialized server hardware is available and preferred for the entire project, as chapters 5 and 6 recommend GPU use but earlier sections can be completed with just a CPU.
- Is LLMs-from-scratch or reasoning-from-scratch more popular on GitHub?
- LLMs-from-scratch has more GitHub stars (102,733 vs 4,998). Stars measure visibility, not whether either tool fits your constraints.
- Are LLMs-from-scratch and reasoning-from-scratch open source?
- Yes - both are open-source projects on GitHub (LLMs-from-scratch: Other, reasoning-from-scratch: Apache-2.0).
- Where can I find alternatives to LLMs-from-scratch or reasoning-from-scratch?
- GraphCanon lists graph-backed alternatives at LLMs-from-scratch alternatives and reasoning-from-scratch alternatives (LLMs-from-scratch markdown twin, reasoning-from-scratch markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, LLMs-from-scratch or reasoning-from-scratch?
- LLMs-from-scratch: Very active. reasoning-from-scratch: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for LLMs-from-scratch and reasoning-from-scratch?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: LLMs-from-scratch trust report; reasoning-from-scratch trust report.