ModelJars
Community marker-JAR catalog for discovering and running local JVM AI models.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
Java 25 or newer - A GPU is optional
- Keys or accounts: HF_TOKEN
download install.sh from GitHub as README instructs (read before executing)
curl -fsSL https://raw.githubusercontent.com/ModelJars/modeljars/main/install.sh -o /tmp/install.shinstall ModelJars CLI 0.1.72 via script; latest has no assets (404)
MODELJARS_CLI_VERSION=0.1.72 sh /tmp/install.sh
Where the README and reality differ
- README: curl -fsSL https://raw.githubusercontent.com/ModelJars/modeljars/main/install.sh | sh installs latest
What worked: MODELJARS_CLI_VERSION=0.1.72 sh /tmp/install.sh needed because v0.1.73 (latest) has 0 assets and returns 404 for modeljars-linux-x86_64
Check that it works
modeljars --version 2>&1; echo ---; modeljars version 2>&1The output should contain “0.1.72”.
What it does
- Search and filter the model catalogNot tested
- Download model weights ahead of timeNot tested
- Check which models this machine can runNot tested
- Generate demo Java programs you can editNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 0 of 4 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- search the qualified model catalog
- check what the current machine can run
- download and verify model weights
An alternative to Ollama.
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 31 Oct 2026
- Version 0.1.72