mlx

Facilitates running and fine-tuning LLMs on Apple Silicon, optimizing performance and model conversion for local development.

Install this skill

92/100

Security score

The mlx skill was audited on Mar 3, 2026 and we found 4 security issues across 2 threat categories. Review the findings below before installing.

medium line 270

Curl to non-GitHub URL

SourceSKILL.md

270	curl http://localhost:8080/v1/chat/completions \

low line 38

External URL reference

SourceSKILL.md

38	MLX-LM supports most popular architectures: Llama, Mistral, Qwen, Phi, Gemma, Cohere, and many more. Check the [mlx-community](https://huggingface.co/mlx-community) on Hugging Face for pre-converted m

low line 270

External URL reference

SourceSKILL.md

270	curl http://localhost:8080/v1/chat/completions \

low line 284

External URL reference

SourceSKILL.md

284	client = OpenAI(base_url="http://localhost:8080/v1", api_key="not-needed")

Scanned on Mar 3, 2026

GitHub Stars 2

Rate this skill

Categorydevelopment

UpdatedMay 21, 2026