pickfit

BrowseLocal AI tools

BitRun

Zero-compile runner and terminal dashboard for 1-bit ternary LLMs on CPU.

Tested on macOS and Linux

Use it

macOS arm64

  1. download install.sh from GitHub

    curl -fsSL https://raw.githubusercontent.com/IshekKhal/bitrun/main/install.sh -o /tmp/install.sh && wc -l /tmp/install.sh && head -n 200 /tmp/install.sh
  2. run install.sh to extract bitrun binaries to ~/.bitrun/bin

    sh /tmp/install.sh

Check that it works

export PATH="$HOME/.bitrun/bin:$PATH" && bitrun --version 2>&1

The output should contain “bitrun version 0.2.0-beta”.

First thing to try

export PATH="$HOME/.bitrun/bin:$PATH" && bitrun hardware 2>&1

Run bitrun hardware to see what your machine offers; you may first need to add $HOME/.bitrun/bin to your PATH.

Linux x86_64

  1. Download install.sh

    curl -fsSL https://raw.githubusercontent.com/IshekKhal/bitrun/main/install.sh -o /tmp/install.sh
  2. Run install script

    sh /tmp/install.sh

Check that it works

export PATH="$HOME/.bitrun/bin:$PATH" && bitrun --version

The output should contain “bitrun version 0.2.0-beta”.

First thing to try

export PATH="$HOME/.bitrun/bin:$PATH" && bitrun hardware

Run bitrun hardware to see what your machine offers; you may first need to add $HOME/.bitrun/bin to your PATH.

What it does

  • Run 1-bit ternary language models on your CPU
    How to use it
    1. Download a model with bitrun pull <model>, for example bitrun pull bitnet-70m.
    2. Run bitrun bench <model> --tokens <number> to generate tokens and see the speed.
    Tested
  • Serve a model through a local OpenAI-compatible API
    How to use it
    1. Start the server with bitrun serve <model> --port <port>.
    2. List models with curl -s http://127.0.0.1:<port>/v1/models.
    3. Send chat requests to http://127.0.0.1:<port>/v1/chat/completions as JSON with a model name and messages.
    Tested
  • Download 1-bit models from Hugging Face
    Not tested
  • Open a full-screen dashboard in the terminal
    Not tested

How far pickfit got

macOS arm64

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

Linux x86_64

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

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

Good for

  • Pull a 1-bit model directly from Hugging Face
  • Launch full-screen dashboard with live hardware telemetry
  • Serve a model via local OpenAI-compatible REST server

How pickfit tested it

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

macOS arm64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.2.0-beta

Differences the test machine hit

  • README: bitrun --help shows usage
    In the test: bitrun --help prints help but exits 1, not 0 (bitrun --version exits 0)

Linux x86_64

It produces model output

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.2.0-beta

Differences the test machine hit

  • README: curl -fsSL ... | sh adds bitrun to PATH
    In the test: Installer appends to ~/.bashrc; current shell needs export PATH="$HOME/.bitrun/bin:$PATH"
  • README: bitrun cockpit <model> launches dashboard
    In the test: Requires /dev/tty; fails in headless sandbox with 'could not open a new TTY'

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.