npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

turboquant

v0.2.6

Published

TurboQuant: Extreme compression for AI models with GGUF and SafeTensors export

Readme

TurboQuant NPM Package

CLI wrapper for TurboQuant Python library - install globally to use turboquant command from anywhere. Features an interactive TUI (Terminal User Interface) when run without arguments.

Installation

Option 1: Global Install (Recommended)

npm install -g turboquant

Then use anywhere:

turboquant --help
turboquant kv-analyze --model-size 70b

Option 2: NPX (No Install)

npx turboquant kv-analyze --model-size 70b

Option 3: From Source

cd /path/to/turboquant-clone/npm-package
npm install -g .

Requirements

  • Node.js 14+
  • Python 3.8+ (for CLI functionality)
  • Bun (optional, for the best TUI experience)

Interactive TUI Mode

Run tq or turboquant without arguments to launch the interactive TUI:

tq                    # Launch interactive TUI (requires Bun)
turboquant            # Same as above

The TUI provides a visual interface for:

  • Download & Quantize: Search and download models from HuggingFace with quantization
  • Quick Compress: Compress .npy files with default settings
  • KV Cache Analysis: Analyze memory usage for LLM KV caches

Installing Bun for TUI

If you don't have Bun installed, you'll see a helpful message. Install it with:

curl -fsSL https://bun.sh/install | bash

Without Bun, the CLI will fall back to standard command-line mode.

CLI Commands

# Compression
turboquant compress input.npy output.tq --bits 3
turboquant decompress output.tq reconstructed.npy
turboquant quick input.npy

# Analysis
turboquant benchmark input.npy --bits 3,4
turboquant kv-analyze --model-size 70b --seq-len 100000

# Model Management
turboquant download TheBloke/Llama-2-7B-GPTQ --bits 4
turboquant list-models

Shortcuts

tq                    # Launch interactive TUI (requires Bun)
tq --help             # Same as turboquant
tq quick input.npy    # Quick compression

Troubleshooting

"Python not found"

Install Python 3.8+ first:

# macOS
brew install python

# Ubuntu/Debian
sudo apt install python3 python3-pip

# Windows
# Download from python.org

"TUI requires Bun runtime"

Install Bun for the interactive TUI:

curl -fsSL https://bun.sh/install | bash

Without Bun, commands still work in CLI mode.

"Permission denied"

Use with sudo (Unix) or run as Administrator (Windows):

sudo npm install -g turboquant

What This Does

This NPM package is a thin wrapper that:

  1. Checks for Python 3.8+
  2. Installs TurboQuant via pip (if not already installed)
  3. Provides an interactive TUI when run without arguments (requires Bun)
  4. Delegates all commands to the Python CLI

The actual quantization algorithms run in Python for performance.

Links

  • GitHub: https://github.com/zapdev-labs/turboquant
  • Issues: https://github.com/zapdev-labs/turboquant/issues
  • Bun: https://bun.sh