pickfit

BrowseLocal AI tools

RigSpark

Hardware-aware CLI that checks if local models fit your hardware and estimates speed.

Tested on Linux

Use it

Linux x86_64

  1. Download prebuilt archive and verify checksum

    mkdir -p /tmp/rigspark-dl && curl -fL -o /tmp/rigspark-dl/rigspark-x86_64-unknown-linux-gnu.tar.gz https://github.com/shashankswe2020-ux/rigspark/releases/download/v3.0.6/rigspark-x86_64-unknown-linux-gnu.tar.gz && echo "d139e9f656e26af006332201810ed0c8b8f21b54c5987c4bc12f24d453d4efae  /tmp/rigspark-dl/rigspark-x86_64-unknown-linux-gnu.tar.gz" | sha256sum -c
  2. Extract archive and install binaries to PATH

    tar xzf /tmp/rigspark-dl/rigspark-x86_64-unknown-linux-gnu.tar.gz -C /tmp/rigspark-dl && cp /tmp/rigspark-dl/rigspark-x86_64-unknown-linux-gnu/rigspark /tmp/rigspark-dl/rigspark-x86_64-unknown-linux-gnu/llmup /tmp/rigspark-dl/rigspark-x86_64-unknown-linux-gnu/rigspark-gui ~/.local/bin/ && chmod +x ~/.local/bin/rigspark ~/.local/bin/llmup ~/.local/bin/rigspark-gui && rigspark --version

Check that it works

rigspark --version

The output should contain “rigspark 3.0.6”.

First thing to try

rigspark recommend

Run rigspark recommend to see which models fit this machine.

What it does

  • Get a yes, slow or no verdict on running a model
    How to use it
    1. Run rigspark recommend to rank models for this machine with a verdict for each.
    2. Run rigspark can-run <model> to check one model before you download it.
    Tested
  • Estimate tokens per second
    Not shown working
  • Pull, verify and serve models
    Not tested
  • Generate images and short videos
    Not tested

How far pickfit got

Linux x86_64

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

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

Good for

  • rank models for this machine
  • check one model before download
  • chat with the active model

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 31 Oct 2026
  • Version 3.0.6

Differences the test machine hit

  • README: cargo binstall rigspark-cli / cargo install rigspark-cli (needs Rust toolchain)
    In the test: downloaded prebuilt rigspark-x86_64-unknown-linux-gnu.tar.gz from GitHub releases, verified SHA-256 and copied rigspark/llmup/rigspark-gui to ~/.local/bin
  • README: rigspark can-run llama3.1:8b
    In the test: can-run exits 1 when the verdict is no; judge by output text not exit 0
  • README: offline yes/slow/no verdicts for this machine
    In the test: container reports 0.0 GiB usable memory with GPU-probe fallback warnings, so every verdict here is no/ram-bound; same commands give yes/slow on real hardware

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.