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
Install arc-llama via uv tool
uv tool install arc-llamaInstall portable Vulkan llama-server runtime
arc-llama install-runtime
Check that it works
arc-llama --version 2>&1The output should contain “arc-llama, version 1.0.0”.
First thing to try
arc-llama doctor 2>&1Run 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 APITested
How to use it
- Start the server with
arc-llama serve --port 11437. - List available models with
curl -s http://127.0.0.1:11437/v1/models.
- Start the server with
- Manage models in the built-in web UITested
How to use it
- Start the server with
arc-llama serve --port 11437. - Open http://127.0.0.1:11437/ in a browser.
- Use the Open WebUI tab to work with your models.
- Start the server with
- Detect Intel Arc GPUs automaticallyNot shown working
- Find and download GGUF modelsNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 2 of 4 features work
- 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'