pickfit

BrowseLocal AI tools

Cluaiz

Local Rust engine that runs GGUF and ONNX models for chat, vision, speech and embeddings.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • A GPU is optional
  1. Download install script without piping to shell

    curl -fsSL https://cluaiz.com/install.sh -o /tmp/cluaiz-install.sh && ls -l /tmp/cluaiz-install.sh && wc -c /tmp/cluaiz-install.sh
  2. Install mac-arm64 core with install script

    sh /tmp/cluaiz-install.sh

Check that it works

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

The output should contain “cluaiz 0.1.0”.

First thing to try

mkdir -p ~/models && curl -fL -o ~/models/stories260K.gguf https://huggingface.co/ggml-org/test-model-stories260K/resolve/main/stories260K-f32.gguf && ls -l ~/models/stories260K.gguf
export PATH="$HOME/.cluaiz/bin:$PATH" && cluaiz show ~/models/stories260K.gguf

Add ~/.cluaiz/bin to your PATH, then run cluaiz show <model.gguf> to inspect a local GGUF model.

Linux x86_64

You need first

  • A GPU is optional
  1. Download installer to /tmp/install.sh for inspection

    curl -fsSL https://cluaiz.com/install.sh -o /tmp/install.sh && wc -c /tmp/install.sh && head -c 4000 /tmp/install.sh
  2. Install Cluaiz release into ~/.cluaiz/bin

    sh /tmp/install.sh
Where the README and reality differ
  • README: curl -fsSL https://cluaiz.com/install.sh | sh
    What worked: download the script first (curl -fsSL https://cluaiz.com/install.sh -o /tmp/install.sh), read it, then run sh /tmp/install.sh
  • README: run cluaiz directly after install
    What worked: binary installs to ~/.cluaiz/bin, which is not on PATH; each use needs export PATH="$HOME/.cluaiz/bin:$PATH" before cluaiz

Check that it works

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

The output should contain “cluaiz 0.1.0”.

First thing to try

export PATH="$HOME/.cluaiz/bin:$PATH" && cluaiz status

Add ~/.cluaiz/bin to your PATH, then run cluaiz show <model.gguf> to inspect a local GGUF model.

What it does

These come from the README; pickfit didn’t check them one by one.

  • Chat with GGUF models
    Not tested
  • Automatically place models on GPU, RAM or CPU
    Not tested
  • Turn text into speech
    Not tested
  • Transcribe speech to text
    Not tested

How far pickfit got

macOS arm64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

Linux x86_64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

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

Good for

  • chat with a local GGUF model in the terminal
  • serve models over an OpenAI-compatible local API
  • transcribe speech to text with local Whisper models
  • generate text and image embeddings locally
  • ingest documents and images into text or vectors

An alternative to llama.cpp.

How pickfit tested it

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

macOS arm64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 29 Oct 2026
  • Version 0.1.0

Differences the test machine hit

  • README: curl -fsSL https://cluaiz.com/install.sh | sh then use cluaiz
    In the test: export PATH="$HOME/.cluaiz/bin:$PATH" before using cluaiz; installer only appends to shell rc files
  • README: cluaiz show unsloth/Qwen3-4B-GGUF
    In the test: cluaiz show accepts a local path (cluaiz show ~/models/stories260K.gguf); registry id would require a large download
  • README: cluaiz serve
    In the test: cluaiz serve takes no model argument; select local file first with cluaiz model set-chat ~/models/stories260K.gguf

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 28 Oct 2026
  • Version 0.1.0

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.