If you want to know how fast a local LLM runs on your hardware, chances are it's pretty confusing.
Benchmarking AI models on real hardware is way harder than it looks. Between AMD, NVIDIA, Apple Silicon, Intel, and Qualcomm, plus hundreds of open source models, getting the test bench right is a challenge.
So we're making it dead simple. We're open sourcing our internal testing harness. Anyone can run open source models on their own hardware and submit results to the public leaderboard at computearena.ai.
It's live now, with a few hundred submissions already.
If you want to know how a specific model performs on a given hardware, chances are the data is already there.
This is the same tool we use internally to track model and chip performance.
Try it out and tell us what to improve!
About Compute:Arena on Product Hunt
“Community submitted benchmarks for Local AI”
Compute:Arena launched on Product Hunt on September 17th, 2026 and earned 80 upvotes and 1 comments, placing #19 on the daily leaderboard. Community-submitted performance benchmarks for local AI models on any hardware, any runtime, any quantisation.
On the analytics side, Compute:Arena competes within Open Source, Artificial Intelligence, GitHub and Apple — topics that collectively have 604.7k followers on Product Hunt. The dashboard above tracks how Compute:Arena performed against the three products that launched closest to it on the same day.
Who hunted Compute:Arena?
Compute:Arena was hunted by Lukas Wesemann. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Compute:Arena including community comment highlights and product details, visit the product overview.
Lukas Wesemann