mlx

mlx is a skill for Claude Code from itsmostafa/llm-engineering-skills. It costs 57 tokens per session (2,492 once invoked), scanned A, original, MIT.

A toolkit for running and fine-tuning large language models locally on Macs with Apple Silicon, such as M1 through M4 chips. It also supports converting models, reducing their memory use, and serving them through an HTTP API.

In plain words
What is it for?
Use it to generate text, chat with local models, convert Hugging Face models to MLX format, apply LoRA or QLoRA fine-tuning, quantize models to 4 or 8 bits, and expose a model through an API.
Why use it?
It lets developers work with language models on a compatible Mac without relying entirely on a remote service, while using shared CPU and GPU memory efficiently.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # ./data/train.jsonl is required for --train.

Part of the llm-engineering-skills plugin — 9 skills shipped together

Good fit Use it to generate text, chat with local models, convert Hugging Face models to MLX format, apply LoRA or QLoRA fine-tuning, quantize models to 4 or 8 bits, and expose a model through an API.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/itsmostafa/llm-engineering-skills
agentmods
npx agentmods add skills/itsmostafa/llm-engineering-skills/mlx

Made for: Claude Code.

Or install llm-engineering-skills, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mlx

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsmostafa/llm-engineering-skills/mlx.svg)](https://agentmods.dev/skills/itsmostafa/llm-engineering-skills/mlx)
Your own site
<a href="https://agentmods.dev/skills/itsmostafa/llm-engineering-skills/mlx"><img src="https://agentmods.dev/badge/skills/itsmostafa/llm-engineering-skills/mlx.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02492
Opus 5 $0.00028 $0.01246
Sonnet 5 $0.00011 $0.00498
Haiku 4.5 $0.00006 $0.00249

Measured 7d ago against content hash 7f1cc9e64abb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mlx scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8080/v1/chat/completions \
skills/mlx/SKILL.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using MLX for LLMs on Apple Silicon

MLX-LM is a Python package for running large language models on Apple Silicon, leveraging the MLX framework for optimized performance with unified memory architecture.

Table of Contents

Core Concepts

Why MLX

Aspect PyTorch on Mac MLX
Memory Separate CPU/GPU copies Unified memory, no copies
Optimization Generic Metal backend Apple Silicon native
Model loading Slower, more memory Lazy loading, efficient
Quantization Limited support Built-in 4/8-bit

MLX arrays live in shared memory, accessible by both CPU and GPU without data transfer overhead.

Supported Models

MLX-LM supports most popular architectures: Llama, Mistral, Qwen, Phi, Gemma, Cohere, and many more. Check the mlx-community on Hugging Face for pre-converted models.

Installation

pip install mlx-lm

Requires macOS 13.5+ and Apple Silicon (M1/M2/M3/M4).

Text Generation

Python API

from mlx_lm import load, generate

# Load model (from HF hub or local path)
model, tokenizer = load("mlx-community/Llama-3.2-3B-Instruct-4bit")

# Generate text
response = generate(
    model,
    tokenizer,
    prompt="Explain quantum computing in simple terms:",
    max_tokens=256,
    temp=0.7,
)
print(response)

Streaming Generation

from mlx_lm import load, stream_generate

model, tokenizer = load("mlx-community/Mistral-7B-Instruct-v0.3-4bit")

prompt = "Write a haiku about programming:"
for response in stream_generate(model, tokenizer, prompt, max_tokens=100):
    print(response.text, end="", flush=True)
print()

Read the full file on GitHub · 338 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 338 lines · 57 tokens per session scan A 7f1cc9e64abb

Subscribe to this mod's changes

mlx is a skill published in the GitHub repository itsmostafa/llm-engineering-skills (23 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 2,492 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

better-prompt

A prompt editor that turns rough instructions for AI systems into clearer, more complete prompts. It follows published OpenAI and Anthropic guidance.

huangwb8/skills · 107 tokens

ai-engineer-expert

Expert-level AI implementation, deployment, LLM integration, and production AI systems. Use when the user mentions AI engineering, LLM, deployment, production AI, or integration, or when the task involves LLM Patterns, LLM Integration, or Production Systems.

personamanagmentlayer/pcl · 58 tokens

bio-prefect-dask-nextflow

Design reproducible bioinformatics pipelines with Prefect plus Dask or Nextflow. Use when scaffolding local, distributed, or scheduler-backed workflows.

fmschulz/omics-skills · 37 tokens

gauntlet

Empirically test whether a skill actually improves model output — before trusting it. Runs a controlled experiment: planted-flaw fixture, no-skill control arm, skill arm(s), optional cross-model arms via installed CLIs, blind judging with shuffled labels, and a pressure test for verdict stability. Produces…

CassioRoos/godfly-skills · 131 tokens

image-prompt

Use when the user wants to turn a short idea into a rich, production-grade image-generation prompt — posters, landing-page or UI mockups, ads, editorial layouts, photoreal scenes, game screenshots, logos, or illustrations. Builds ONE structured, copy-paste-ready prompt optimized for gpt-image-2 by default, following…

veryCoolTimo/imagegen-skills · 148 tokens

toolshed

Toolshed — durable, model-agnostic working state for ONE coding task (feature, fix, investigation) as docs/work/SLUG/ under docs/, DELETED at close. NOT the Workbench product/MCP (Slack highlights app). Seeds STATE + decisions/questions/evidence with grades and reproduction commands. Use for "start a toolshed", "seed…

CassioRoos/godfly-skills · 165 tokens