Skip to content

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++

docs: the 12 GB card's prompt figures are withdrawn - a five-pair repeat read +254% and -20.5% where the first read +35% and +17%, and that box's prompt swings 218-466 tok/s between arms

Niko12211ee6060afba9
diff --git a/docs/release-notes-0.2.7.md b/docs/release-notes-0.2.7.md
index 91122a6b9..c0345964d 100644
--- a/docs/release-notes-0.2.7.md
+++ b/docs/release-notes-0.2.7.md
@@ -50,8 +50,7 @@ on the RTX 3060 12 GB (IQ3_XXS), five interleaved pairs of fresh engines:
|---|---|---|
| decode story | 45.9 | **61.6 (+34.1%)** |
| decode code | 43.6 | **73.1 (+67.6%)** |
-| prompt 1K | 333.6 | **451.5 (+35.3%)** |
-| prompt 4K, in a 4K context | 248.5 | **291.0 (+17.1%)** |
+| prompt | **not claimed** - this box's prompt read swings between 218 and 466 tok/s across runs, and a repeat of the same five-pair A/B read +254% and -20.5% where the first read +35% and +17% |
| decode behind a 4K document | 45.1 | **62.2 (+37.9%)** |
It holds where it matters most: with **two conversations in flight** the whole recipe reads **31.2 -> 62.0 tok/s aggregate