pickfit

BrowseDeveloper CLIs

FitLLM Engine

Checks whether a local LLM fits on a GPU or Apple Silicon Mac with architecture-aware memory math.

Tested on Linux

Use it

Linux x86_64

  1. Install fitllm-engine globally via npm

    npm install -g fitllm-engine

Check that it works

fitllm --help

The output should contain “exit codes: 0 fits”.

First thing to try

fitllm "Gemma 4 12b" --gpu "RTX 4090"

Run fitllm "<model name>" --gpu "<GPU name>" to check whether a model fits your GPU.

What it does

  • Check if a model fits your GPU
    How to use it
    1. Run fitllm "<model name>" --gpu "<GPU name>".
    2. Read the verdict, which shows the GPU memory, quantization and context size.
    Tested
  • Rank models that fit your hardware
    How to use it
    1. Run fitllm --top --gpu <GPU name>.
    2. Read the ranked list, which shows memory use and maximum context for each model.
    Tested
  • Scan downloaded Ollama and LM Studio models
    Not shown working
  • Detect your local GPU automatically
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 2 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • check one model against a GPU or Mac and return fit verdict
  • rank supported local models that fit given hardware
  • detect local GPUs and list what fits as JSON

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 2.22.0

Differences the test machine hit

  • README: npm install fitllm-engine
    In the test: npm install -g fitllm-engine puts fitllm on PATH via ~/.local prefix; README examples use npx fitllm
  • README: --version or --help check (only --help works)
    In the test: use fitllm --help; fitllm --version is parsed as a model name and exits 2 with unknown model

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.