v0.2.13

Run a big AI model on your own PC

Your data never leaves the machine. Works on NVIDIA and AMD, Windows and Linux — free and open source.

Get started What's new in v0.2.13

See benchmarksCommunityView source on GitHub

Strata brings Qwen three point eight Flash Next to your own PC. Private, fast, and open source.

v0.2.13

Strata 0.2.13

Strata 0.2.13: new DFlash2 defaults per card, a faster app start, a fix for the Strix Halo Terminal launch, and Qwen4 groundwork The app and the Terminal are 0.2.13. Control and every engine package are 0.1.59. The update feed is sequence 124 (the DGX Spark feed stays 123). The D…

Download Releases

Nothing leaves your PC

Once installed, the model and your chats stay on this computer.

60+ tokens/s on a good GPU

Compare speed, power cost, and payback time on the benchmarks page.

Plugs into your coding assistant

Paste one address and Cursor or Claude Code can use it.

Worth reading now

Project Maya deep dive: running GLM-5.3-Flash (321B MoE) on your own NVIDIA GPUs, built on Strata
@coldniko · 34 days ago · Releases · Benchmarks
New release is out!
@coldniko · 35 days ago · Releases · Benchmarks
Strata wins by a tight margin against other Strix Halo inference engines on first try release
@coldniko · 36 days ago · Releases · Benchmarks
Strata wins by a tight margin against all other Strix Halo inference engines in it’s first try release. Did not expect that! 🥳 https://t.co/7Ie0lXa85c
@coldniko · 36 days ago · Releases · Benchmarks

What people say →

Guides

Start with the question you have. Each guide ends by pointing at the next step.

Guides →GPUs →GPU brands →Editorial pages →

Let your AI install Strata

Set up Strata on this PC for me: https://github.com/Niko1221/Strata - follow docs/AI_SETUP.md in that repository.

From the author

Latest from @coldniko.

See all →