v0.2.19
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.

v0.2.19
Strata 0.2.19
Strata 0.2.19 The app and the Terminal are 0.2.19. The engines (strata-engine, the new strata-inkling shape engine, and the updated Linux SYCL strata-hy4 package) are 0.1.65, and so is Control, the program that installs and updates them. The update feeds are sequence 131 (shared)…

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 · 46 days ago · Releases · Benchmarks
- New release is out!
@coldniko · 46 days ago · Releases · Benchmarks
- Strata wins by a tight margin against other Strix Halo inference engines on first try release
@coldniko · 47 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 · 47 days ago · Releases · Benchmarks
Guides
Start with the question you have. Each guide ends by pointing at the next step.
- Maya model sizing: how much VRAM plus RAM a local LLM needs
- Stratat's JustAResearcher/gpu-unlock-ada model lets you run Llama 2 13B locally without Nvidia GPU
- Stratat introduces Nanbeige/Nanbeige4.3-33B, a locally runnable LLM for edge AI
- Zagitta/gpu-unlock: run large AI models on your own GPU with the Strata engine
- Introducing the DeepSeek-V4.1-Flash-1017 GGUF model for local AI with Stratat
- Carbon-X model on Stratat: run large biology models locally
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.
- Project Maya deep dive: running GLM-5.3-Flash (321B MoE) on your own NVIDIA GPUs, built on Strata
- Small patch coming in approx 1h for this issue
- Only loses to @ciruai engine on Hermes benchmarks. Kudos 🫡