---
title: "pmetal vs Made-With-ML"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/epistates-pmetal-vs-gokumohandas-made-with-ml"
tools: ["epistates-pmetal", "gokumohandas-made-with-ml"]
---

# pmetal vs Made-With-ML

*GraphCanon updated Jul 15, 2026*

## Verdict

Pick pmetal when pmetal is primarily Rust; Made-With-ML is Jupyter Notebook; pick Made-With-ML when made-With-ML is primarily Jupyter Notebook; pmetal is Rust.

[pmetal](https://pmetal.io) reports 303 GitHub stars, 22 forks, and 7 open issues, last pushed Jun 5, 2026. [Made-With-ML](https://madewithml.com) has 49k stars, 7.7k forks, and 27 open issues, last pushed Mar 4, 2026. Figures are from public GitHub metadata via [pmetal's repository](https://github.com/Epistates/pmetal) and [Made-With-ML's repository](https://github.com/GokuMohandas/Made-With-ML).

| | [pmetal](/tools/epistates-pmetal.md) | [Made-With-ML](/tools/gokumohandas-made-with-ml.md) |
| --- | --- | --- |
| Tagline | PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration. | Learn how to develop, deploy and iterate on production-grade ML applications. |
| Stars | 303 | 48,703 |
| Forks | 22 | 7,661 |
| Open issues | 7 | 27 |
| Language | Rust | Jupyter Notebook |
| Adopt for | - | - |
| Persona | - | - |
| Runtime | - | - |
| License | Other | MIT |
| Categories | Inference & Serving, LLM Frameworks, Model Training | AI Agents, LLM Frameworks, Model Training |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [pmetal](/tools/epistates-pmetal.md) | [Made-With-ML](/tools/gokumohandas-made-with-ml.md) |
| --- | --- | --- |
| Maintenance | Steady (60%) | Slowing (36%) |
| Days since push | 39d | 132d |
| Open issues (now) | 7 | 27 |
| Owner type | Organization | User |
| Full report | [trust report](/tools/epistates-pmetal/trust.md) | [trust report](/tools/gokumohandas-made-with-ml/trust.md) |

## Shared compatibility

- **Python**: [pmetal](/tools/epistates-pmetal.md) - Python runtime; [Made-With-ML](/tools/gokumohandas-made-with-ml.md) - Python runtime

## Choose when

### Choose pmetal if…

- pmetal is primarily Rust; Made-With-ML is Jupyter Notebook.
- License: pmetal is Other, Made-With-ML is MIT.
- Tags unique to pmetal: ai, ane, apple-silicon, distillation.
- Also covers Inference & Serving.

### Choose Made-With-ML if…

- Made-With-ML is primarily Jupyter Notebook; pmetal is Rust.
- License: Made-With-ML is MIT, pmetal is Other.
- Tags unique to Made-With-ML: data-engineering, data-quality, data-science, distributed-ml.
- Also covers AI Agents.

## When NOT to use pmetal

- Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic.
- 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.

## When NOT to use Made-With-ML

- Last GitHub push was 132 days ago (slowing maintenance, Mar 4, 2026). Validate activity before betting a new project on Made-With-ML.
- AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism.
- 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.

## Common questions

### What is the difference between pmetal and Made-With-ML?

pmetal: PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.. Made-With-ML: Learn how to develop, deploy and iterate on production-grade ML applications.. See the comparison table for live GitHub stats and shared categories.

### When should I choose pmetal over Made-With-ML?

Choose pmetal over Made-With-ML when pmetal is primarily Rust; Made-With-ML is Jupyter Notebook; License: pmetal is Other, Made-With-ML is MIT; Tags unique to pmetal: ai, ane, apple-silicon, distillation; Also covers Inference & Serving.

### When should I choose Made-With-ML over pmetal?

Choose Made-With-ML over pmetal when Made-With-ML is primarily Jupyter Notebook; pmetal is Rust; License: Made-With-ML is MIT, pmetal is Other; Tags unique to Made-With-ML: data-engineering, data-quality, data-science, distributed-ml; Also covers AI Agents.

### When should I avoid pmetal?

Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. 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.

### When should I avoid Made-With-ML?

Last GitHub push was 132 days ago (slowing maintenance, Mar 4, 2026). Validate activity before betting a new project on Made-With-ML. AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. 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.

### Is pmetal or Made-With-ML more popular on GitHub?

Made-With-ML has more GitHub stars (48,703 vs 303). Stars measure visibility, not whether either tool fits your constraints.

### Are pmetal and Made-With-ML open source?

Yes - both are open-source projects on GitHub (pmetal: Other, Made-With-ML: MIT).

### Where can I find alternatives to pmetal or Made-With-ML?

GraphCanon lists graph-backed alternatives at [pmetal alternatives](/tools/epistates-pmetal/alternatives) and [Made-With-ML alternatives](/tools/gokumohandas-made-with-ml/alternatives) ([pmetal markdown twin](/tools/epistates-pmetal/alternatives.md), [Made-With-ML markdown twin](/tools/gokumohandas-made-with-ml/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/epistates-pmetal-vs-gokumohandas-made-with-ml.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, pmetal or Made-With-ML?

pmetal: Steady. Made-With-ML: Slowing. 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 pmetal and Made-With-ML?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [pmetal trust report](/tools/epistates-pmetal/trust); [Made-With-ML trust report](/tools/gokumohandas-made-with-ml/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=epistates-pmetal`](/api/graphcanon/graph?tool=epistates-pmetal)
- 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/_