What do you want to do?
3 use cases
-
Find which open models your machine can run
Run llmfit to see your hardware and a ranked list of models that fit.
View prompt
Run AlexsJones/llmfit and list the top five recommended models for my hardware with their quantization. Confirm the detected GPU and RAM match my system.
-
Get model recommendations as JSON for scripts
Use recommend with --json and a use case to feed other tools.
- REPO
AlexsJones/llmfit - Software and DevOps
- Intermediate
View prompt
Run `llmfit recommend --json` and return the top three model names for coding on this machine.
- REPO
-
Measure real tokens per second on your hardware
Download, serve and benchmark a model from the TUI, then optionally share results.
- REPO
AlexsJones/llmfit - Software and DevOps
- Intermediate
View prompt
Use llmfit to benchmark <model> on this machine and report measured tokens per second versus the estimate.
- REPO
Quick start with llmfit
- Check you have what it needs: macOS, Windows, Linux or Docker.
- Open AlexsJones/llmfit on GitHub and read the README and license.
- Install with
brew install llmfitoruv tool install -U llmfit - Run
llmfitfor the interactive TUI - Browse models ranked for your hardware
- Pick one and download it
These steps come from our top use case, Find which open models your machine can run, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for AlexsJones/llmfit
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers deciding which local models to download for their machine.
- Why it is hot38k stars
- LanguageRust
- Sourcegithub.com/AlexsJones/llmfit · Back to Hot repos
Requirements
- macOS, Windows, Linux or Docker
Add this badge to your README
Maintain llmfit? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/alexsjones-llmfit/?utm_source=github&utm_medium=badge&utm_campaign=AlexsJones-llmfit)
HTML
<a href="https://dedupedai.com/use-cases/alexsjones-llmfit/?utm_source=github&utm_medium=badge&utm_campaign=AlexsJones-llmfit"><img src="https://dedupedai.com/badge/AlexsJones/llmfit.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about llmfit
What is llmfit?
llmfit inspects your CPU, RAM, GPU and VRAM and recommends which open-source LLMs and quantizations your hardware can comfortably run, with a TUI, JSON output and real benchmark runs. It is an open-source project on GitHub: https://github.com/AlexsJones/llmfit.
Who is llmfit for?
Developers deciding which local models to download for their machine.
What can I do with llmfit?
3 use cases so far, for example: Find which open models your machine can run; Get model recommendations as JSON for scripts; Measure real tokens per second on your hardware. Each has steps and a copy-paste agent prompt.
What do I need to run llmfit?
macOS, Windows, Linux or Docker.
What are alternatives to llmfit?
Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.
Is llmfit safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.