EuLLM
Platform for creating, distributing and running sovereign EU-compliant LLMs locally.
Tested on LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 2 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
crates:quinn-proto 0.11.14Quinn: Remote memory exhaustion in quinn-proto from unbounded out-of-order stream reassembly (GHSA-4w2j-m93h-cj5j, high, fixed in 0.11.15)
See 1 more
crates:quinn-proto 0.11.14— RUSTSEC-2026-0340 (high), fixed in 0.11.18
Linux x86_64
download installer script
curl -fsSL https://raw.githubusercontent.com/eullm/eullm/main/installer/install.sh -o /tmp/eullm-install.shrun installer, verifies checksum into ~/.local/bin
sh /tmp/eullm-install.sh
Check that it works
eullm --versionThe output should contain “eullm 0.8.5 (CPU)”.
First thing to try
mkdir -p ~/models && curl -fL -o ~/models/stories260K.gguf https://huggingface.co/ggml-org/test-model-stories260K/resolve/main/stories260K-f32.gguf && ls -l ~/models/stories260K.ggufeullm run ~/models/stories260K.ggufcurl -s http://localhost:11434/v1/modelsStart a model with eullm run <model.gguf>, then send requests to the API at http://localhost:11434.
What it does
- Make structured decisions without generating textTested
How to use it
- Start a model with
eullm run <model.gguf>. - Send your text and questions with choices and criteria: `curl -s http://localhost:11434/v1/systemone -H 'Content-Type: application/json' -d '{"model": "<model>", "state": "<your text>", "questions": {
- Read the chosen answer, probabilities and confidence in the reply.
- Start a model with
- Run GGUF models locallyTested
How to use it
- Start a GGUF model with
eullm run <model.gguf>. - Chat with it: `curl -s http://localhost:11434/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "<model>", "messages": [{"role": "user", "content": "<your text>"}], "temperature":
- Start a GGUF model with
- Serve an Ollama and OpenAI compatible APITested
How to use it
- Start a model with
eullm run <model.gguf>. - List available models:
curl -s http://localhost:11434/v1/models
- Start a model with
- Adapt models to a domain and languageNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 3 of 4 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- route, escalate or close a support ticket
- triage an incoming email by team, urgency and legitimacy
- accept, reject or send a document to review
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
It produces model output
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version eullm 0.8.5 (CPU) [a3bbe56fc2b6]
Differences the test machine hit
- README: docs start server with `eullm serve --decision-model ...` then POST /v1/systemone without a model field
In the test: name the loaded file in "model": "stories260K" when server was started with `eullm run ~/models/stories260K.gguf`; without it /v1/systemone returns model_not_loaded