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
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 --versionThe 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/nullRun 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 performanceNot tested
- Watch GPU stats during inferenceNot tested
- See live MoE expert routingNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- Main function works
- 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