pickfit

BrowseLocal AI tools

arc-llama

Command-line tool that detects Intel Arc GPUs and serves GGUF models via OpenAI-compatible API.

Tested on Linux

Use it

Linux x86_64

  1. Install arc-llama via uv tool

    uv tool install arc-llama
  2. Install portable Vulkan llama-server runtime

    arc-llama install-runtime

Check that it works

arc-llama --version 2>&1

The output should contain “arc-llama, version 1.0.0”.

First thing to try

arc-llama doctor 2>&1

Run arc-llama doctor to check your setup, then arc-llama serve --port 11437 to start the server.

What it does

  • Serve models through an OpenAI-compatible API
    How to use it
    1. Start the server with arc-llama serve --port 11437.
    2. List available models with curl -s http://127.0.0.1:11437/v1/models.
    Tested
  • Manage models in the built-in web UI
    How to use it
    1. Start the server with arc-llama serve --port 11437.
    2. Open http://127.0.0.1:11437/ in a browser.
    3. Use the Open WebUI tab to work with your models.
    Tested
  • Detect Intel Arc GPUs automatically
    Not shown working
  • Find and download GGUF models
    Not tested

How far pickfit got

Linux x86_64

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

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

Good for

  • Run an OpenAI-compatible server for GGUF models
  • Detect Intel Arc GPUs and write starter config
  • Auto-register GGUF models found under scan paths

How pickfit tested it

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

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.0.0

Differences the test machine hit

  • README: pip install arc-llama
    In the test: uv tool install arc-llama (isolated install avoids PEP 668 / read-only system)
  • README: arc-llama init writes starter config and registers GPUs
    In the test: On a box with no Intel GPU, init/doctor/gpus exit 2 with 'No Intel GPUs detected' and no config is written; add/scan then refuse with 'No GPUs in config'

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.