pickfit

BrowseLocal AI tools

mdma

LLM inference engine for owned hardware with custom kernels, exact memory admission and private federation.

Use it

Before you install: known vulnerabilities

pickfit found 6 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:zip 8.6.0 zip: Critical Parser Differential & Security Control Bypass via Dual-Header Inconsistencies (Zip Cloaking) Leading to Arbitrary File Overwrite & RCE (GHSA-m665-v7pm-7grj, critical, fixed in 9.0.5)
See 5 more

Linux x86_64

You need first

  • Runtimes: Rust 1.99+
  • A GPU is optional

These steps ran from a folder named work in the home folder, which already existed. Make it and run them from there:

mkdir -p "$HOME/work" && cd "$HOME/work"
  1. git clone the mdma source (depth 1) into work/src and cargo build --release --features cli,service (about 9 minutes)

    cd "$HOME"/work && git clone --depth 1 https://github.com/seuros/mdma src && cd src && cargo build --release --features cli,service
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

cd /home/sbx/work && git clone --depth 1 https://github.com/seuros/mdma src && cd src && cargo build --release --features cli,service
cd /home/sbx/work/src && target/release/mdma --version
cd /home/sbx/work/src && target/release/mdma info

Check that it works

cd "$HOME"/work/src && target/release/mdma --version

The output should contain “mdma 0.6.0”.

First thing to try

cd "$HOME"/work/src && target/release/mdma info

What it does

  • Run LLMs on CPU, ROCm, Vulkan, CUDA, Metal
    Tested
  • Exact memory admission before model loading
    Tested
  • Serve models over mTLS gRPC
    Tested
  • Federate inference across trusted peers
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 3 of 4 features work
  4. Works offline

macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • inventory hardware of a machine
  • smoke-test compiled backends on a machine
  • estimate whether a model fits before loading
  • run local greedy text generation from a GGUF
  • serve models over mTLS gRPC server

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 16 Nov 2026
  • Version mdma 0.6.0

Differences the test machine hit

  • README: cargo build --release --features cli,service (run in the repository root)
    In the test: The work dir had only README.md, so the source had to be cloned first: git clone https://github.com/seuros/mdma, then build inside it. The build took about 9 minutes on this box.
  • README: Rust 1.99+ (mise.toml pins it)
    In the test: The build succeeded with the box's Rust 1.100.0 for the cli,service feature set; the 1.99 requirement was not tested separately.
  • README: mdma doctor smoke-tests compiled backends
    In the test: Only cpu was built and ready. Doctor also printed warnings that dmidecode and lspci are missing (no root, no pciutils); these are warnings, not failures.
  • README: target/release/mdma-run /path/to/model.gguf "The capital of France is" 16
    In the test: Worked as written with the stories260K GGUF on CPU; output is greedy text.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.