- Strata is a free open-source project that enables large AI models with 125 billion parameters (Qwen3.8-Flash-Next) to run on typical gaming PCs running Windows or Linux with NVIDIA or AMD graphics cards of at least 12GB.
- It requires at least 32GB RAM and about 80GB of storage space. During installation, it automatically detects the graphics card and recommends an appropriate model size and settings, supporting download and execution.
- This model overcomes memory limits by utilizing GPU, RAM, CPU, and SSD in a distributed manner, reads long texts at over 1,000 tokens per second, and generates answers at speeds ranging from 53 to 93 tokens per second depending on GPU performance (benchmarks measured by the development team on two gaming PCs).
- Compatible with OpenAI APIs for integration with other apps and coding agents, and since it runs locally, data is not transmitted to external clouds.
There's a notice saying that during the first installation, the RAM from 35 to 55 GB may be locked for a long time and the PC could freeze. Since it requires a heavy memory load during the initial loading phase before it becomes usable, whether users can tolerate this will be a key factor in deciding to adopt local execution. It would be good to experience this initial process considering your PC's performance and your work patterns.