--- title: "mlx-tune vs LLMs-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/arahim3-mlx-tune-vs-rasbt-llms-from-scratch" tools: ["arahim3-mlx-tune", "rasbt-llms-from-scratch"] --- # mlx-tune vs LLMs-from-scratch *GraphCanon updated Jul 11, 2026* ## Verdict Pick mlx-tune when mlx-tune is primarily Python; LLMs-from-scratch is Jupyter Notebook; pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; mlx-tune is Python. [mlx-tune](https://arahim3.github.io/mlx-tune/) reports 1.4k GitHub stars, 88 forks, and 11 open issues, last pushed Jun 23, 2026. [LLMs-from-scratch](https://amzn.to/4fqvn0D) has 99k stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. Figures are from public GitHub metadata via [mlx-tune's repository](https://github.com/ARahim3/mlx-tune) and [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch). | | [mlx-tune](/tools/arahim3-mlx-tune.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Tagline | Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API. | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | | Stars | 1,351 | 98,899 | | Forks | 88 | 15,183 | | Open issues | 11 | 4 | | Language | Python | Jupyter Notebook | | Adopt for | - | 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. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Other | | Categories | LLM Frameworks, Model Training, Vector Databases | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [mlx-tune](/tools/arahim3-mlx-tune.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Maintenance | Active (82%) | Steady (60%) | | Days since push | 17d | 38d | | Open issues (now) | 11 | 4 | | Security scan | 46 low (46 low) | No lockfile | | Full report | [trust report](/tools/arahim3-mlx-tune/trust.md) | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | ## Decision facts: LLMs-from-scratch - **Adopt for:** 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. ## Choose when ### Choose mlx-tune if… - mlx-tune is primarily Python; LLMs-from-scratch is Jupyter Notebook. - License: mlx-tune is Apache-2.0, LLMs-from-scratch is Other. - Tags unique to mlx-tune: llm-finetuning, lora, llm, large-language-models. - Also covers Vector Databases. ### Choose LLMs-from-scratch if… - LLMs-from-scratch is primarily Jupyter Notebook; mlx-tune is Python. - License: LLMs-from-scratch is Other, mlx-tune is Apache-2.0. - Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention-mechanism, from-scratch. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ## When NOT to use mlx-tune - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## 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丰 - a deeper learning experience. ## Common questions ### What is the difference between mlx-tune and LLMs-from-scratch? mlx-tune: Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories. ### When should I choose mlx-tune over LLMs-from-scratch? Choose mlx-tune over LLMs-from-scratch when mlx-tune is primarily Python; LLMs-from-scratch is Jupyter Notebook; License: mlx-tune is Apache-2.0, LLMs-from-scratch is Other; Tags unique to mlx-tune: llm-finetuning, lora, llm, large-language-models; Also covers Vector Databases. ### When should I choose LLMs-from-scratch over mlx-tune? Choose LLMs-from-scratch over mlx-tune when LLMs-from-scratch is primarily Jupyter Notebook; mlx-tune is Python; License: LLMs-from-scratch is Other, mlx-tune is Apache-2.0; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention-mechanism, from-scratch; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I avoid mlx-tune? LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### 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丰 a deeper learning experience. ### Is mlx-tune or LLMs-from-scratch more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 1,351). Stars measure visibility, not whether either tool fits your constraints. ### Are mlx-tune and LLMs-from-scratch open source? Yes - both are open-source projects on GitHub (mlx-tune: Apache-2.0, LLMs-from-scratch: Other). ### Where can I find alternatives to mlx-tune or LLMs-from-scratch? GraphCanon lists graph-backed alternatives at [mlx-tune alternatives](/tools/arahim3-mlx-tune/alternatives) and [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) ([mlx-tune markdown twin](/tools/arahim3-mlx-tune/alternatives.md), [LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md)), 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](/compare/arahim3-mlx-tune-vs-rasbt-llms-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, mlx-tune or LLMs-from-scratch? mlx-tune: Active. LLMs-from-scratch: Steady. 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 mlx-tune and LLMs-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [mlx-tune trust report](/tools/arahim3-mlx-tune/trust); [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=arahim3-mlx-tune`](/api/graphcanon/graph?tool=arahim3-mlx-tune) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_