pickfit

BrowseLocal AI tools

Lumen

Rust binary that runs Qwen LLMs GPU-resident locally and serves OpenAI-compatible API.

Tested on LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 1 known high or critical vulnerability in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:rustls-webpki 0.103.10 rustls-webpki: Denial of service via panic on malformed CRL BIT STRING (GHSA-82j2-j2ch-gfr8, high, fixed in 0.103.13)

Linux x86_64

You need first

  • A GPU is optional
  • Needs the network
  1. download install script

    curl -fsSL -o /tmp/install.sh https://servelumen.com/install.sh
  2. install lumen binaries via script

    bash /tmp/install.sh

Check that it works

lumen --version

The output should contain “lumen v0.51.0”.

First thing to try

lumen pull qwen3.5-9b:q4_0 --yes
lumen-server qwen3.5-9b:q4_0 --port 8000
curl -fsSL http://127.0.0.1:8000/v1/models

What it does

Good for

  • generate text from a prompt with a local Qwen model
  • serve OpenAI-compatible chat completions with streaming
  • generate an image from a text prompt

An alternative to llama.cpp.

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Produces output
  4. Works offline

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

How pickfit tested it

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

Linux x86_64

It produces model output

  • Replayed from scratch
  • GPU: Tesla T4
  • Works offline
  • Checked on 1 Nov 2026
  • Version v0.51.0

Differences the test machine hit

  • README: curl -fsSL https://servelumen.com/install.sh | bash
    In the test: download with curl -fsSL -o /tmp/install.sh, read /tmp/install.sh fully, then run bash /tmp/install.sh
  • README: no CUDA SDK needed
    In the test: installer auto-fetched NVIDIA NVRTC + cuBLAS 12.9 (670 MB) into ~/.local/lib/lumen because the box has a driver but no CUDA toolkit
  • README: lumen run qwen3.5-9b:q8_0
    In the test: used qwen3.5-9b:q4_0 (~5.5 GB LBC) instead of README q8_0; Q4_0 is the smallest quant for the 9B and is verified on T4 cc 7.5

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.