Guide
Will running Strata wear out your SSD?
On two Arc Pro B60s, eight warm Strata requests recorded 16.0 MB of reads and 0.70 MB of writes on the model SSD. Here’s how to measure your own setup.
Guides and test reports from real machines. Each test report gives the conditions of its runs.
Guide
On two Arc Pro B60s, eight warm Strata requests recorded 16.0 MB of reads and 0.70 MB of writes on the model SSD. Here’s how to measure your own setup.
Test report
Flash-Next loaded on one B60. With two, it took nearly eight minutes longer to start and passed all 24 coding, extraction and tool-decision attempts.
Test report
The model took 13 minutes to load from our hard-drive archive. Once warm, the median passing reply took 2.70 seconds.
Test report
Four streams moved the queue faster, with a longer wait for replies to start. Here’s how to test the tradeoff on your own server.
Guide
Liquid AI’s small agent-focused model is a timely option to investigate. Task reliability and model-specific backend support still need their own evidence.
Guide
Read the startup token budget, leave room for the answer, and distinguish a model that loads from a workload that runs reliably.
Guide
Reuse a document or conversation prefix to save prompt processing. Here is how to tell whether that matches your workload—and how to compare it fairly.
News
The Intel GPU backend gets a targeted compilation fix. No LocalXPU speed or stability improvement has been measured.
Guide
Chat, coding agents and batch jobs need different measurements. Here's a checklist for comparing local inference setups.
News
The release includes Intel GPU packages and a tagged container. Python support and browser access defaults have changed too.