TurboLLM
Runs local LLM engines auto-tuned to GPU with web UI and compatible API.
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.
npm:brace-expansion 5.0.6brace-expansion: DoS via exponential-time expansion of consecutive non-expanding {} groups (GHSA-3jxr-9vmj-r5cp, high, fixed in 5.0.7)npm:undici 8.5.0undici vulnerable to TLS certificate validation bypass via dropped tls options in Agent (GHSA-2m5v-pch6-74hx, high, fixed in 8.12.2)
See 8 more
npm:brace-expansion 5.0.6— GHSA-6j4f-fj2g-mc7p (high), fixed in 5.0.10npm:brace-expansion 5.0.6— GHSA-mh99-v99m-4gvg (high), fixed in 5.0.8npm:brace-expansion 5.0.6— GHSA-qhr7-859c-m2p7 (high), fixed in 5.0.11npm:brace-expansion 5.0.6— GHSA-rgw5-rvv9-x895 (high), fixed in 5.0.9npm:undici 8.5.0— GHSA-4cwx-7wf7-3272 (high), fixed in 8.9.0npm:undici 8.5.0— GHSA-4w7w-5xrc-9h26 (high), fixed in 8.12.2npm:undici 8.5.0— GHSA-qrxm-fqhp-jwvm (high), fixed in 8.12.2npm:undici 8.5.0— GHSA-rfgv-xxqx-mfg5 (high), fixed in 8.10.2
3 more findings not listed here.
Linux x86_64
You need first
- Runtimes:
node>=22
install turbollm globally via npm
npm install -g turbollm
Check that it works
turbollm --helpThe output should contain “--port <n>”.
First thing to try
turbollm --port 6996 --no-open --no-telemetry 2>&1curl -s http://127.0.0.1:6996/api/v1/statusRun turbollm --port 6996 --no-open --no-telemetry to start the server, then open http://127.0.0.1:6996/ in a browser.
What it does
- Chat with models in a web UITested
How to use it
- Start the server with
turbollm --port 6996 --no-open --no-telemetry. - Open http://127.0.0.1:6996/ in your browser to reach the TurboLLM web UI.
- Start the server with
- Run any local LLM engineNot shown working
- Tune engines to your GPU automaticallyNot shown working
- Point Claude Code at your own machineNot shown working
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
- Point Claude Code at your own machine
- Browse and download GGUF models from Hugging Face
- Copy the exact launch command for a loaded model
An alternative to LM Studio and Ollama.
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 1 Nov 2026
- Version 1.15.0