Find the AI Model Best Suitable for Your Hardware
Whichllm is a tool that allows you to identify the native large language models that perform best on your hardware. Focusing on current benchmarks rather than the number of parameters, this Python-based software allows you to choose the most suitable model with a single command.
Updates
- November 5, 2026: Stars 6,817 → 6,822, latest release v0.6.4 (November 4, 2026).
- November 3, 2026: Stars 6,803 → 6,817, latest release v0.6.0 (November 2, 2026).
- October 29, 2026: Stars 6,767 → 6,803, latest release v0.5.23 (October 28, 2026).
- October 19, 2026: Stars 6,719 → 6,767, latest release v0.5.21 (October 19, 2026).
What you get
- It determines the native language model best suited to your hardware with up-to-date benchmark data.
- It predicts performance by automatically detecting GPU and system features.
- It offers the opportunity to download models, start chats and create Python code samples with a single command.
Installation
uv tool install whichllm
uv tool upgrade whichllm # update an existing installbrew install andyyyy64/whichllm/whichllm
pip install whichllmRunning it
whichllmwhichllm run "qwen 2.5 1.5b gguf"If you don't write code
Using the Whichllm tool, I want to list the local big language models that best suit my hardware specifications and see the performance estimates of these models. How can I filter the models with the highest benchmark scores based on the GPU or CPU capacity in my system, as well as plan the hardware required for a particular model?
Repository: https://github.com/Andyyyy64/whichllm. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-09: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.