Vortelio
Open-source local platform to run LLMs and generate images, audio, video, and 3D offline.
Tested on LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 13 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
go:golang.org/x/crypto v0.51.0golang.org/x/crypto vulnerable to auth bypass via unenforced @revoked status (GHSA-5cgq-3rg8-m6cv, critical, fixed in 0.52.0)go:github.com/go-jose/go-jose/v4 v4.1.4Go JOSE: DoS when parsing JWKs that contain RSA keys (GHSA-mgcc-cww5-fp2q, high, fixed in 4.1.6)
See 8 more
go:golang.org/x/crypto v0.51.0— GHSA-89gr-r52h-f8rx (critical), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-f5wc-c3c7-36mc (critical), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-jppx-rxg9-jmrx (critical), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-rm3j-f69w-wqmq (critical), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-vgwf-h737-ff37 (critical), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-x527-x647-q7gg (critical), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-q4h4-gmj2-qvw2 (high), fixed in 0.52.0go:golang.org/x/crypto v0.51.0— GHSA-w879-237q-wc7r (high), fixed in 0.52.0
3 more findings not listed here.
Linux x86_64
You need first
- A GPU is optional
install vortelio via uv tool from git subdirectory
uv tool install "git+https://github.com/metiutek/Vortelio#subdirectory=vortelio-pip"
Where the README and reality differ
- README: uv tool install "git+https://github.com/metiu1/Vortelio#subdirectory=vortelio-pip" (ranking used metiu1)
What worked: canonical GitHub owner is metiutek, URL https://github.com/metiutek/Vortelio works; metiu1 typo fails
Check that it works
curl -s http://localhost:11500/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"bartowski--smollm2-135m-instruct-gguf:q8-0","messages":[{"role":"user","content":"Hello"}],"temperature":0,"max_tokens":16}' 2>&1The output should contain “"object":"chat.completion"”.
First thing to try
vortelio pull "llm/hf.co/bartowski/SmolLM2-135M-Instruct-GGUF:SmolLM2-135M-Instruct-Q8_0.gguf" 2>&1vortelio serve --port 11500curl -s http://localhost:11500/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"bartowski--smollm2-135m-instruct-gguf:q8-0","messages":[{"role":"user","content":"Hello"}],"temperature":0,"max_tokens":16}' 2>&1Run vortelio serve --port 11500 to start the local server, then send requests to it at http://localhost:11500.
What it does
- Run LLMs on your own machineTested
How to use it
- Download a model with
vortelio pull "llm/hf.co/<repo>:<model file>.gguf". - Start the server with
vortelio serve --port 11500. - Send a chat request with
curl -s http://localhost:11500/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"<model name>","messages":[{"role":"user","content":"<your text>"}]}'.
- Download a model with
- Generate images with Stable DiffusionNot tested
- Transcribe audio offline with WhisperNot tested
- Generate video on your own machineNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 1 of 4 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- run LLMs locally
- generate images locally with Stable Diffusion
- transcribe audio offline with Whisper
- generate video locally
- generate 3D models from text or images
An alternative to Ollama, LM Studio and ComfyUI.
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 31 Oct 2026
- Version 0.4.6