pickfit

BrowseDeveloper CLIs

llm-visuals

Live terminal dashboard monitoring a locally running LLM server and GPUs.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Rust toolchain 1.75+
  • System packages: nvidia-smi, xpu-smi, macmon
  1. Download prebuilt binary tarball and install to local bin

    curl -fsSL -o /tmp/llm-visuals.tar.gz https://github.com/DingoOz/llm-visuals/releases/download/v0.14.0/llm-visuals-0.14.0-linux-x86_64.tar.gz && tar xzf /tmp/llm-visuals.tar.gz -C /tmp && mkdir -p ~/.local/bin && cp /tmp/llm-visuals ~/.local/bin/llm-visuals && chmod +x ~/.local/bin/llm-visuals

Check that it works

llm-visuals --version

The output should contain “llm-visuals 0.14.0”.

First thing to try

TERM=xterm-256color script -qec "stty rows 44 cols 140; timeout 3 llm-visuals --demo --log-db off" /dev/null

Run llm-visuals --demo in a terminal to see the dashboard with sample data, or llm-visuals while your local LLM server is running.

What it does

These come from the README; pickfit didn’t check them one by one.

  • Watch live LLM inference performance
    Not tested
  • Watch GPU stats during inference
    Not tested
  • See live MoE expert routing
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Main function works
  4. Works offline

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

Good for

  • monitor tokens per second and time to first token
  • view live GPU load and memory usage
  • check context fill and speculative-decoding acceptance
  • see which layers are busy on which GPU
  • inspect MoE expert routing for the last token

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 0.14.0

Differences the test machine hit

  • README: cargo install --path . with Rust toolchain 1.75+
    In the test: Downloaded prebuilt linux-x86_64 tarball from GitHub releases (v0.14.0) and copied single binary to ~/.local/bin instead of building
  • README: cargo run --release -- --demo / llm-visuals --demo
    In the test: Run demo under a pty with terminal size set: TERM=xterm-256color script -qec "stty rows 44 cols 140; timeout 3 llm-visuals --demo --log-db off" /dev/null; direct run fails with 'No such device or address' and tiny pty renders only escape init

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.