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
download install.sh for inspection
curl -fsSL -o /tmp/install.sh https://raw.githubusercontent.com/shifulegend/project-zero/master/install.shinstall 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 --versionThe 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.ggufpz --model ~/models/stories260K.gguf --prompt "What is the capital of France?" --threads 2Run 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 CPUNot tested
- Run several model families from one programNot tested
- Run DeepSeek-V2 MoE modelsNot tested
- Run Mamba-1 state-space modelsNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- Produces output
- 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