pickfit

BrowseLocal AI tools

Project Zero

CPU-only LLM inference engine in C that runs GGUF models via CLI and web chat.

Tested on Linux

Use it

Linux x86_64

You need first

  • System packages: GCC, make
  1. download install.sh for inspection

    curl -fsSL -o /tmp/install.sh https://raw.githubusercontent.com/shifulegend/project-zero/master/install.sh
  2. install pz with script --yes --no-wizard

    sh /tmp/install.sh --yes --no-wizard
Where the README and reality differ
  • README: pz --help lists every flag (implies normal zero exit)
    What worked: pz --help prints the full help text but exits 1; pz --version exits 0 and confirms install

Check that it works

pz --version

The output should contain “Project Zero v0.2.0”.

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 -lh ~/models/stories260K.gguf
pz --model ~/models/stories260K.gguf --prompt "What is the capital of France?" --threads 2

Run a prompt against a GGUF model with pz --model <model.gguf> --prompt "<your text>" --threads 2.

What it does

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

  • Run BitNet b1.58 models on the CPU
    Not tested
  • Run several model families from one program
    Not tested
  • Run DeepSeek-V2 MoE models
    Not tested
  • Run Mamba-1 state-space models
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Produces output
  4. Works offline

Good for

  • run ternary models on CPU
  • serve models over OpenAI-compatible API with web chat
  • run prompt inference on a GGUF model

An alternative to llama.cpp, ik_llama.cpp and bitnet.cpp.

How pickfit tested it

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

Linux x86_64

It produces model output

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version v0.2.0

Differences the test machine hit

  • README: curl -fsSL https://raw.githubusercontent.com/shifulegend/project-zero/master/install.sh | sh
    In the test: installer downloads a checksum-verified prebuilt binary tarball project-zero-0.2.0-x86_64-unknown-linux-gnu.tar.gz which cannot be read as text before running; checksum was verified during install
  • README: pz --model <file.gguf> --server --port 8080
    In the test: first server start auto-calibrates SIMD backends for ~35s before listening; subsequent starts and CLI runs are fast

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.