mlx-serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/ddalcu/mlx-serve with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/ddalcu/mlx-serve'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/ddalcu--mlx-serve)HTML
<a href="/listings/ddalcu--mlx-serve"><img src="/api/listings/ddalcu--mlx-serve/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
brew tap ddalcu/mlx-serve https://github.com/ddalcu/mlx-serve brew trust ddalcu/mlx-serve brew install --cask mlx-serve # the app (recommended) brew install mlx-serve # CLI + server only, no GUI
To upgrade, name the package (the app also updates itself from its menu):
brew update brew upgrade --cask mlx-serve # the app brew upgrade mlx-serve # the CLI
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 141 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- 
- # MLX-Serve
- Run open models on your Mac: chat, coding agents, images, video, music, speech and 3D. One native app and one local server that speaks the OpenAI, Anthropic and Ollama APIs. It runs offline, needs no Python and no account, and it's MIT licensed.
- [](https://github.com/ddalcu/mlx-serve/releases/latest)
- [](https://github.com/ddalcu/mlx-serve/releases)
- [](https://github.com/ddalcu/mlx-serve/stargazers)
- [](LICENSE)
- **[Download for Mac](https://github.com/ddalcu/mlx-serve/releases/latest/download/MLX-Serve.dmg)** · [Homebrew](#install) · [iPhone](https://apps.apple.com/us/app/mlx-chat-local-ai/id6787603518) · [Linux](#linux-and-windows) · [mlxserve.com](https://mlxserve.com/) · [简体中文](README.zh-CN.md)
- 
- ## Install
- **The app.** [Download MLX-Serve](https://github.com/ddalcu/mlx-serve/releases/latest/download/MLX-Serve.dmg), drag it to Applications and open it. It needs macOS 26.2 or later on Apple Silicon, suggests a model that fits your Mac, and updates itself.
- **Homebrew.**
- ```bash
- brew tap ddalcu/mlx-serve https://github.com/ddalcu/mlx-serve
- brew trust ddalcu/mlx-serve
- brew install --cask mlx-serve # the app
- brew install mlx-serve # or only the command-line server
- ```
- **The terminal**, if you know Ollama:
- ```bash
- mlx-serve run gemma4 # downloads Gemma 4 E4B, serves it and chats right here
- mlx-serve pull gemma4:26b # download only, resumable
- mlx-serve serve # serve everything you downloaded; models load when asked for
- ```
- The server listens on `http://localhost:11234`. Point any OpenAI, Anthropic or Ollama client at it, or open that address in a browser for the built-in web console.
- ### iPhone
- [MLX-Serve](https://apps.apple.com/us/app/mlx-chat-local-ai/id6787603518) puts the same engine on your iPhone: chat with Gemma 4, clone your voice, and make pictures and music, all on the phone and offline. It needs an A17 Pro-class iPhone or newer with iOS 26.
- ### Linux and Windows
- Every release has Linux downloads for NVIDIA GPUs: x64 for RTX 20 to 50 cards, arm64 for DGX Spark, GH200 and Jetson Thor. On Windows with an NVIDIA card, one script builds it. Details are in [docs/building.md](docs/building.md#linux-and-windows-nvidia).
- ## What it does
- - **Coding agents on a local model.** `mlx-serve launch claude` starts Claude Code against your Mac, set up with the model's real context window. Codex, OpenCode, pi, Grok and others work the same way. [Integrations](docs/integrations.md)
- - **Pictures, video, music, speech and 3D.** FLUX.2, Qwen-Image, Krea, MOSS-Image, LTX-Video, MiniMax-H3, ACE-Step, YuE2, Qwen3-TTS with voice cloning, and Hunyuan3D, in the app or over HTTP. [The app](docs/app.md)
- - **Transcripts and meeting notes.** Speech to text in 30 languages, with word timings and who said what. The menu bar records a call and writes the notes. [API](docs/api.md#other-endpoints)
- - **Models bigger than your Mac.** GLM-5.3-Flash and DeepSeek-V4.1-Flash run on a 128 GB Mac by reading their experts from the SSD. Two Macs on a Thunderbolt 5 cable can run one model together, and Macs on your network can use each other's models. [CLI](docs/cli.md) · [FAQ](docs/faq.md#can-my-macs-share-models-over-the-network)
- - **An assistant that lives on your Mac.** Chat with your documents, talk to it hands-free, give agents a sandboxed shell and MCP tools, or schedule tasks in plain English. [The app](docs/app.md)
- - **The APIs your tools already use.** OpenAI chat, completions and Responses, Anthropic Messages and Ollama, all on one port, with streaming, tool calls, JSON schemas, vision and reasoning. [API](docs/api.md)
- ## What can my Mac run?
- The app suggests a first model for your Mac's memory:
- | Memory | Suggested model |
- |---|---|
- | 16 GB | Gemma 4 E4B |
- | 18–24 GB | Gemma 4 12B |
- | 32 GB | Qwen 3.8 27B |
- | 36 GB | Qwen 3.8 27B 6-bit |
- | 48–64 GB | Qwen 3.8 27B 8-bit |
- | 96 GB and up | Qwen3.8-Flash-Next (125B, about 6B active per token) |
- | 128 GB | Also GLM-5.3-Flash and DeepSeek-V4.1-Flash, their experts streamed from the SSD |
- | 256 GB | Also GLM-5.3-Flash in memory (NVIDIA's FP4 pack) |
- Thousands more run too: any MLX model with a supported architecture, and any GGUF. The [tier list](https://mlxserve.com/llm-tier-list/) ranks the popular ones, and [docs/models.md](docs/models.md) lists every architecture.
- ## Speed
- Decode speed in v26.11.1 on an M5 Ultra with 256 GB, on a code prompt, with speculative decoding on:
- | Model | Tokens per second |
- |---|---:|
- | Qwen3.6 35B-A3B, 4-bit | 421 |
- | Qwen3.8 27B, 4-bit | 243 |
- | Gemma 4 E4B, 4-bit | 200 |
- | Gemma 4 26B-A4B, 4-bit | 184 |
- | Qwen3.8-Flash-Next, 4.7 bits | 180 |
- On an M4 Max, the same models decode 10% to 51% faster than they did in v26.8. Every release is measured the same way in [benchmarks.md](benchmarks.md); speculative decoding and tuning are in [docs/performance.md](docs/performance.md).
- ## Docs
- - [Integrations](docs/integrations.md): Claude Code, Codex, OpenCode, pi, Zed and more
- - [HTTP API](docs/api.md): OpenAI, Anthropic, Ollama and the media endpoints
- - [CLI and server flags](docs/cli.md)
- - [The Mac app](docs/app.md), with the media tour
- - [Supported models](docs/models.md)
- - Write a plugin without rebuilding the server: [model](docs/plugin-model.md), [media](docs/plugin-media.md), [quant](docs/plugin-quant.md)
- - [Performance and tuning](docs/performance.md)
- - [Building from source](docs/building.md) and [NVIDIA GPUs](docs/CUDA.md)
- - [FAQ](docs/faq.md) and the [changelog](CHANGELOG.md)
- ## Build from source
- You need Xcode 26.2 or later and [Homebrew](https://brew.sh):
- ```bash
- git clone --recurse-submodules https://github.com/ddalcu/mlx-serve && cd mlx-serve
- ./app/build.sh
- ```
- The script fetches the pinned Zig, builds MLX and llama.cpp, and signs the app ad hoc. There's no Python anywhere in the build. Server-only builds are in [docs/building.md](docs/building.md).
- ## Community
- Questions, ideas and things you made: the [community chat on X](https://x.com/i/chat/group_join/g2108335256541741397/K38XS6aGRh) and [GitHub issues](https://github.com/ddalcu/mlx-serve/issues). Builds and deep dives go out on [YouTube](https://www.youtube.com/@DavidDalcu) and [X](https://x.com/ddalcu).
- ## Thank you
- Thank you to the sponsors who back mlx-serve: @jcprichard, @skudinov, @davidfekke, @lojza3d, @cpko, @d-b, @alinselea, Johnny Dang and @R0xr1te. If it's useful to you, you can support it on [GitHub Sponsors](https://github.com/sponsors/ddalcu) or [Buy Me a Coffee](https://buymeacoffee.com/ddalcu). Nothing is paywalled: it's MIT now and stays MIT.
- Thank you also to everyone who sends code, reports and ideas. The [contributors page](https://github.com/ddalcu/mlx-serve/graphs/contributors) shows the code side, and the [changelog](CHANGELOG.md) thanks people release by release.
- ## Acknowledgements
- mlx-serve builds on [MLX](https://github.com/ml-explore/mlx), [mlx-c](https://github.com/ml-explore/mlx-c), [mlx-lm](https://github.com/ml-explore/mlx-lm), [llama.cpp](https://github.com/ggerganov/llama.cpp), [antirez/ds4](https://github.com/antirez/ds4), [mlx-stream](https://github.com/davidtai/mlx-stream), [Sushi](https://github.com/beamivalice/sushi), [jinja.cpp](https://github.com/wangzhaode/jinja.cpp), [nlohmann/json](https://github.com/nlohmann/json), [stb_image](https://github.com/nothings/stb), [libwebp](https://chromium.googlesource.com/webm/libwebp), [Hugging Face tokenizers](https://github.com/huggingface/tokenizers) and [Zig](https://ziglang.org). It runs the open models their authors published, and the app uses the [Anthropic](https://github.com/anthropics/swift-sdk) and [MCP](https://github.com/modelcontextprotocol/swift-sdk) Swift SDKs.
- Licenses and required notices are in [NOTICE](NOTICE). If we missed you, please open a PR.
- ## Star history
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="docs/star-history-dark.svg">
- <img alt="GitHub star history for ddalcu/mlx-serve" src="docs/star-history.svg">
- </picture>
- <!-- regenerate with: python3 scripts/star-chart.py -->
- [](https://trendshift.io/repositories/43025)
- If mlx-serve is useful to you, a star helps other people find it.
- ## License
- MIT, see [LICENSE](LICENSE). Bundled third-party code keeps its own license: [NOTICE](NOTICE) lists it with the required attributions, and [LICENSE-APACHE-2.0](LICENSE-APACHE-2.0) has the Apache license text.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.