Skip to main content

A zero-config Python CLI that detects local hardware and prints S–F grades for AI models

Project description

   _____                       _                 
  / ____|                     (_)                
 | |     __ _ _ __   __ _ _ __ _ _   _ _ __ ___  
 | |    / _` | '_ \ / _` | '__| | | | | '_ ` _ \ 
 | |___| (_| | | | | (_| | |  | | |_| | | | | | |
  \_____\__,_|_| |_|\__,_|_|  |_|\__,_|_| |_| |_|

caniarun 🚀

Not sure if your rig can handle that shiny new AI model? That's exactly what this tool is for!

caniarun checks out your hardware (GPU, CPU, and RAM) and tells you straight up which open-source AI models will actually run on your machine. Instead of throwing confusing metrics at you, it gives you a fun, easy-to-understand vibe check for over 80 models across different compression levels.

You'll get ratings like:

  • 🧈 Smooth as butter
  • 🔥 Dope run
  • 😐 Meh usable
  • 🐌 Laggy vibes
  • 🗑️ Trash mode

Note: This project is a fork from the original canirun.ai, simplified into a script that anyone can easily run directly from their terminal.

Installation

Getting started is super easy. Just drop this in your terminal:

pip install caniarun

(Optional) If you're rocking an NVIDIA GPU and want more precise detection, use this instead:

pip install caniarun[nvidia]

How to Use

Just type this in and hit enter. We'll handle the rest!

caniarun

🌟 Check out the source code & contribute:
github.com/netssv/can_ia_run

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

caniarun-0.1.0.tar.gz (152.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

caniarun-0.1.0-py3-none-any.whl (50.3 kB view details)

Uploaded Python 3

File details

Details for the file caniarun-0.1.0.tar.gz.

File metadata

  • Download URL: caniarun-0.1.0.tar.gz
  • Upload date:
  • Size: 152.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for caniarun-0.1.0.tar.gz
Algorithm Hash digest
SHA256 b3b601dfef62a4adcf23b9d21e8fee31a6c0dbb0fef4657c26821f3596c9470c
MD5 c5b1bf6230a9699cec1c3f2fce9ef2a4
BLAKE2b-256 3d2f309085e50c410b55376bc8fd94ce934a8537e09cc38bd0ee77806ddd0a16

See more details on using hashes here.

Provenance

The following attestation bundles were made for caniarun-0.1.0.tar.gz:

Publisher: workflow.yml on netssv/can_ia_run

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file caniarun-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: caniarun-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 50.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for caniarun-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 305689bf7525cc0f80d9c06b6df00c3d2be948ee6e21e78767681c84e0b6624b
MD5 09e5b09357003aad1eebae8480fc337c
BLAKE2b-256 4f21d841c4ef9f38451fa4b31b491cf3b8da57e5207f353bd8c44bb1833af91e

See more details on using hashes here.

Provenance

The following attestation bundles were made for caniarun-0.1.0-py3-none-any.whl:

Publisher: workflow.yml on netssv/can_ia_run

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page