What's my local ai?
Find the best local model for your machine
16 followers
Find the best local model for your machine
16 followers
We detect your hardware right in your browser and tells you which local models to run with Ollama or LM Studio. Nothing leaves your machine.
Free
Launch Team / Built With
Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second
Promoted
We built this because running AI locally is great and it's not obvious what's the best model *right now* on your hardware.
The website detects your specs in the browser, shows the best model for your machine, and hands you the exact run command.
What does it recommend for your setup? We added a share button just for that!
Love that it estimates from VRAM! Any plans to go further and actually benchmark the machine (real tokens/sec) instead of estimating? That'd be the killer feature for me.
@skander_garroum great question! The benchmark is indeed on our roadmap already because it can help us recommend better models (in reality we won't be able to make a more accurate estimate of the VRAM via a tok/sec metric but it'd still help the user to understand the real potential of their machine)