Run open AI models on your own computer: chat, images, video and voice. RigSpark checks your memory, GPU and disk first and shows what will actually run. No account, no cloud, no meter. Free and open source (MIT), in Rust, for macOS, Windows and Linux.
Hi Product Hunt, I'm Shashank, and I built RigSpark.
RigSpark fixes the first step of running AI locally: knowing whether a model will actually run on your machine before you download 30 to 40 GB. It reads your memory, GPU and disk and shows which models and sizes fit, which will be slow, and which won't run, with the reason.
Then it runs them for you: chat, images, video and voice, all on your own computer. No account, no cloud, nothing metered.
It's free and open source (MIT), written in Rust, and has shipped 38 releases since August. It works on macOS, Windows and Linux, as a desktop app or a command-line tool.
I'd love your feedback on two things: which model did it say your machine can't run that you wish it could, and what should the next catalog update include?
If it's useful, a star on GitHub helps more people find it: github.com/rigspark/rigspark
This is the part of running AI locally that always tripped me up — not picking a model, but knowing whether it would actually run on my machine before downloading gigabytes of weights. Checking memory, GPU and disk first and being upfront about what won't fit is exactly the right first step. Curious about the ones you flag as slow — do you give any sense of how slow they'd actually be, or is it more of a fit / slow / won't-run bucket?
Does it also tell you how fast a model will be on your machine, or only whether it fits?
cool launch!! curious if the estimate accounts for stuff already eating ram, a browser alone can make a model that fits suddenly crawl
About RigSpark on Product Hunt
“Know which AI to run on your own computer”
RigSpark launched on Product Hunt on November 11th, 2026 and earned 77 upvotes and 7 comments, placing #22 on the daily leaderboard. Run open AI models on your own computer: chat, images, video and voice. RigSpark checks your memory, GPU and disk first and shows what will actually run. No account, no cloud, no meter. Free and open source (MIT), in Rust, for macOS, Windows and Linux.
RigSpark was featured in Open Source (69.1k followers), Developer Tools (523k followers), Artificial Intelligence (483.5k followers) and GitHub (41.5k followers) on Product Hunt. Together, these topics include over 282.8k products, making this a competitive space to launch in.
Who hunted RigSpark?
RigSpark was hunted by Shashank Mishra. 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.
Want to see how RigSpark stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Shashank Mishra
Hi Product Hunt, I'm Shashank, and I built RigSpark.
RigSpark fixes the first step of running AI locally: knowing whether a model will actually run on your machine before you download 30 to 40 GB. It reads your memory, GPU and disk and shows which models and sizes fit, which will be slow, and which won't run, with the reason.
Then it runs them for you: chat, images, video and voice, all on your own computer. No account, no cloud, nothing metered.
It's free and open source (MIT), written in Rust, and has shipped 38 releases since August. It works on macOS, Windows and Linux, as a desktop app or a command-line tool.
I'd love your feedback on two things: which model did it say your machine can't run that you wish it could, and what should the next catalog update include?
If it's useful, a star on GitHub helps more people find it: github.com/rigspark/rigspark