Agent Native

transformers-to-mlx

Converts Hugging Face transformers language models to MLX format for inference on Apple Silicon.

by Hugging FaceOfficial publisher

Identity proven by GitHub's verified organisation badge (huggingface)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
No license stated
Pin
1800e73pinned Oct 9, 2026
Context cost
about 6,800 tokenswhen the skill loads
GitHub stars
51on huggingface/transformers-to-mlx
Scripts
7 scripts

What it does

“Convert Hugging Face transformers language models to MLX format for Apple Silicon inference. Use when asked to convert a model from transformers to MLX, port a model to MLX, create an MLX implementation of a model, or test/validate an MLX model conversion. Triggers include mentions of "convert to MLX", "MLX implementation", "port to MLX", "mlx-lm", or requests involving both transformers and MLX frameworks.”
The author's description, from SKILL.md

Generated summary from the skill's own text

Converts Hugging Face transformers language models to MLX format for inference on Apple Silicon. The skill analyzes source model architecture, creates an MLX implementation, validates numerical correctness through generation and layer-by-layer comparison, and submits a pull request to mlx-lm with quantized variants.

When to use it

  • User requests converting a transformers model to MLX format
  • Porting a language model to run on Apple Silicon devices
  • Creating an MLX implementation of a transformers architecture
  • Validating or testing an existing MLX model conversion

When not to

  • The model is not a language model or is vision-only
  • Model is already in MLX format or native quantized weights
  • User needs to run inference immediately without implementation work

Install

No license stated: install from the publisher's repository, and ask the author before you reuse or share it.

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add huggingface/transformers-to-mlx --skill transformers-to-mlx

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install huggingface/transformers-to-mlx transformers-to-mlx@1800e733dc99edf6b33c4c631c813e880dc9cb8f

Installs the commit we checked (1800e73).

Copy by hand

Download the folder at 1800e73 and put it in .claude/skills/transformers-to-mlx for Claude Code and in .agents/skills/transformers-to-mlx for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 1800e73

Claude Code plugin

/plugin install huggingface-skills@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "transformers-to-mlx" by Hugging Face.

Source, pinned to commit 1800e733dc99edf6b33c4c631c813e880dc9cb8f:
https://github.com/huggingface/transformers-to-mlx/tree/1800e733dc99edf6b33c4c631c813e880dc9cb8f/skills/transformers-to-mlx

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/transformers-to-mlx/ for Claude Code and .agents/skills/transformers-to-mlx/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Its license is restricted or not stated. Show me the license terms from the repository before you copy anything.

Listing and checks: https://www.agentnative.dev/skills/hugging-face/transformers-to-mlx

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at 1800e73

Files

18 files, 117 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 1800e73
All 40 skills from Hugging Face

More from Hugging Face

  • hf-cloud-aws-context-discovery

    This skill reads the user's local AWS configuration to discover their active profile, region, account ID, and caller identity before any AWS work begins.

    Claude Code, Codex, Cursor +4 · about 830 tokens · pinned 7 days ago

  • hf-cloud-python-env-setup

    Sets up an isolated Python environment for SageMaker and AWS work with the correct Python version (3.10, 3.11, or 3.12) and current boto3 and awscli.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 1.5K tokens · pinned 7 days ago

  • hf-cloud-sagemaker-deployment-planner

    This skill helps users plan and execute deployments of machine learning models to Amazon SageMaker by gathering requirements, selecting appropriate deployment…

    Claude Code, Codex, Cursor +4 · about 1.9K tokens · pinned 7 days ago

  • hf-cloud-sagemaker-iam-preflight

    This skill validates or creates an AWS IAM execution role before deploying SageMaker endpoints, training jobs, or models.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 1.6K tokens · pinned 7 days ago

  • hf-cloud-sagemaker-production-defaults

    Deploys SageMaker endpoints with production defaults: autoscaling based on traffic, CloudWatch alarms for latency and errors, and consistent tagging.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 6.7K tokens · pinned 7 days ago

  • hf-cloud-serving-image-selection

    This skill helps select the correct SageMaker serving container image for model deployments and retrieves its current URI from AWS's Deep Learning Containers…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 4.3K tokens · pinned 7 days ago

All Coding workflow skills

Related in Coding workflow

  • maintainer-review

    This skill helps maintainers assess GitHub issues and PRs by evaluating whether claimed problems are real, whether existing features already solve them, and…

    by OpenAIOfficial publisher

    Claude Code, Codex, Cursor +4 · about 8.9K tokens · pinned 7 days ago

  • huggingface-tool-builder

    This skill builds reusable command-line scripts and utilities that call the Hugging Face API to fetch, enrich, or process model and dataset metadata.

    by Hugging FaceOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 1.4K tokens · pinned 7 days ago

  • maintainer-review

    Evaluates GitHub issues and PRs through a systematic desk review to assess demonstrated need, existing workarounds, design correctness, and maintainer impact.

    by OpenAIOfficial publisher

    Claude Code, Codex, Cursor +4 · about 8.3K tokens · pinned 7 days ago

  • nemo-automodel-model-onboarding

    This skill guides adding or modifying model architecture support in NeMo AutoModel, covering discovery of model type from config, implementation of custom…

    by NVIDIAOfficial publisher

    Claude Code, Codex, Cursor +3 · about 5.6K tokens · pinned 7 days ago

  • dd-file-issue

    This skill helps file GitHub issues to the DataDog/pup repository for bugs, feature requests, and documentation problems related to the pup CLI, agents, and…

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +3 · about 2.2K tokens · pinned 7 days ago

  • cpu-kernels

    This skill guides agents in writing and optimizing C++ CPU kernels with AVX2 and AVX512 intrinsics for x86 processors, targeting the Hugging Face kernels…

    by Hugging FaceOfficial publisher

    Contains scripts

    Claude Code · about 6.5K tokens · pinned 7 days ago

Open roles at Hugging Face

3 open roles on the jobs board

See all 3 roles at Hugging Face on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use