# Strata 0.2.9 has been released. I ran a quick benchmark, but it doesn't seem to differ from the previous version

**URL:** <http://gitLair.com/t/strata-0-2-9-has-been-released-i-ran-a-quick-benchmark-but-it-doesnt-seem-to-differ-from-the-previous-version/96>\
**Category:** General\
**Created:** [October 31, 2026, 4:57pm UTC](http://gitLair.com/t/strata-0-2-9-has-been-released-i-ran-a-quick-benchmark-but-it-doesnt-seem-to-differ-from-the-previous-version/96 "2026-10-31T16:57:03Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Shawn](http://gitLair.com/user_avatar/gitLair.com/shawn/32/54_2.png) [@Shawn](http://gitLair.com/u/Shawn)\
**Post date:** [October 31, 2026, 4:57pm UTC](http://gitLair.com/t/strata-0-2-9-has-been-released-i-ran-a-quick-benchmark-but-it-doesnt-seem-to-differ-from-the-previous-version/96/1 "2026-10-31T16:57:03Z")

</div>

Strata 0.2.9 has been released. I ran a quick benchmark, but it doesn’t seem to differ from the previous version. Using an RTX 5070 Ti and 64GB of RAM with the Qwen 3.8FN IQ3\_S model, I’m seeing an average decode speed of 85 t/s, with prefill speeds occasionally exceeding 2,700 t/s. Even with a context length of over 120K—pushing toward 150K tokens—the loading is so fast that the difference is clearly noticeable in daily use. That said, given my memory constraints, running any larger models isn’t an option.

 ![HV9Gt5dbkAAzBGN](http://gitLair.com/uploads/default/original/1X/3a5f5b90fed21490049c17b3f2f97d69c1cbadfa.png)