DEDUPED Hot AI repos, turned into use cases Get the Monday 5
138 stars · Rust

How to use Mlxtop: what you can do with it

What is Mlxtop? mlxtop is a terminal dashboard that shows memory, paging, GPU and live tokens per second for local LLM runtimes such as oMLX, Ollama, llama.cpp and vLLM.

How do I use it? Install Mlxtop with brew install maximpri/tap/mlxtop, or use the install script from the README on Linux and macOS; then start your runtime and send it a prompt so a model is loaded; run mlxtop to open the dashboard. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Find why a local model slowed down

    Read memory, paging, GPU and runtime speed side by side to see which one changed.

    View prompt
    Using the mlxtop repo at maximpri/mlxtop, run `mlxtop --once` on <target machine> while the local model served at <endpoint> is responding slowly. Report the verdict line and whether it names memory pressure, paging, a model partly on the CPU, a full card or heat throttling. Verify the report includes tokens per second and memory figures before you state a cause.

  • Check a remote model server over SSH

    Print a text report of a headless machine's local LLM health without opening a dashboard.

    View prompt
    Using the mlxtop repo at maximpri/mlxtop, connect to <target machine> over SSH, run `mlxtop doctor` and then `mlxtop --once`, and return both outputs. Verify that the doctor output lists the runtime connection status before you summarise memory and tokens per second from the report.

  • Spot an Ollama model partly running on the CPU

    See which loaded Ollama models use VRAM, context size and CPU or GPU placement.

    View prompt
    Using the mlxtop repo at maximpri/mlxtop, start a loaded Ollama model on <target machine>, run `mlxtop --once`, and report the loaded model name, its VRAM use and its CPU/GPU placement. Verify the report shows the placement before you say whether the model is partly on the CPU.

Quick start with Mlxtop

  1. Check you have what it needs: macOS 11 or later on Apple Silicon, Linux (x86_64 or ARM64), or Windows (x86_64); A local LLM runtime such as oMLX, Ollama, llama.cpp or vLLM installed and able to serve a model; A terminal, or Rust 1.88 or newer if you build from source.
  2. Open maximpri/mlxtop on GitHub and read the README and license.
  3. Install Mlxtop with brew install maximpri/tap/mlxtop, or use the install script from the README on Linux and macOS.
  4. Start your runtime and send it a prompt so a model is loaded.
  5. Run mlxtop to open the dashboard.
  6. Watch view 1 · Overview while the model answers and read the verdict line.

These steps come from our top use case, Find why a local model slowed down, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for maximpri/mlxtop

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Mlxtop alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and operators who run local LLMs on their own machine or server and need to find out why a model has slowed down.
  • Why it is hot138 stars, launched 45 days ago
  • LanguageRust
  • Sourcegithub.com/maximpri/mlxtop · Back to Hot repos

Requirements

  • macOS 11 or later on Apple Silicon, Linux (x86_64 or ARM64), or Windows (x86_64)
  • A local LLM runtime such as oMLX, Ollama, llama.cpp or vLLM installed and able to serve a model
  • A terminal, or Rust 1.88 or newer if you build from source

Add this badge to your README

Maintain Mlxtop? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/maximpri/mlxtop.svg)](https://dedupedai.com/use-cases/maximpri-mlxtop/?utm_source=github&utm_medium=badge&utm_campaign=maximpri-mlxtop)

HTML 

<a href="https://dedupedai.com/use-cases/maximpri-mlxtop/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=maximpri-mlxtop"><img src="https://dedupedai.com/badge/maximpri/mlxtop.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Mlxtop

What is Mlxtop?

mlxtop is a terminal dashboard that shows memory, paging, GPU and live tokens per second for local LLM runtimes such as oMLX, Ollama, llama.cpp and vLLM. It is an open-source project on GitHub: https://github.com/maximpri/mlxtop.

How do I use Mlxtop?

Install Mlxtop with brew install maximpri/tap/mlxtop, or use the install script from the README on Linux and macOS; then start your runtime and send it a prompt so a model is loaded; run mlxtop to open the dashboard. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Mlxtop for?

Developers and operators who run local LLMs on their own machine or server and need to find out why a model has slowed down.

What can I do with Mlxtop?

3 use cases so far, for example: Find why a local model slowed down; Check a remote model server over SSH; Spot an Ollama model partly running on the CPU. Each has steps and a copy-paste agent prompt.

What do I need to run Mlxtop?

macOS 11 or later on Apple Silicon, Linux (x86_64 or ARM64), or Windows (x86_64); A local LLM runtime such as oMLX, Ollama, llama.cpp or vLLM installed and able to serve a model; A terminal, or Rust 1.88 or newer if you build from source.

What are alternatives to Mlxtop?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Mlxtop safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.