diff --git a/recipes/qwen3-8-flash-next-exl3-5-05bpw-2x-cmp-170hx-tp2-mtp3-morrowmake/recipe.yaml b/recipes/qwen3-8-flash-next-exl3-5-05bpw-2x-cmp-170hx-tp2-mtp3-morrowmake/recipe.yaml
index 13333220b..457b36886 100644
--- a/recipes/qwen3-8-flash-next-exl3-5-05bpw-2x-cmp-170hx-tp2-mtp3-morrowmake/recipe.yaml
+++ b/recipes/qwen3-8-flash-next-exl3-5-05bpw-2x-cmp-170hx-tp2-mtp3-morrowmake/recipe.yaml
@@ -146,3 +146,4 @@ provenance:
     - 'https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe'
     - 'https://huggingface.co/turboderp/Qwen3.8-Flash-Next-exl3'
   notes: 'Recipe by Morrowmake, release v1.0.0 (2026-10-16), repo pinned at 207867e80430701f85f5e99157b03f705ff79ef0 = tag qwen38-recipe-1.0.0; ingested by localai-recipes from the Morrowmake engine-repo watch. Benchmarks upstream-measured 2026-10-15 (MiaAI-Lab protocol; 1 user = median of 10 runs over two boots, 2/4/8 users = median aggregate of 3 runs on one boot; prompt reading = median of 9 cold prefills). Serving defaults are locked by serve.sh (MAX_LEN=262144, GPU_UTIL=0.95, LAYOUT=tp2; FIRST_LIGHT=1 is a 32K/eager/no-MTP diagnostic, not serving). PLE placement ssd is the engine default; ram/device are comparison placements. EXL3 sm_80 kernel switches ship on by default with six one-variable kill switches (off: +18% single-user decode, +43-56% at 2-8 users). P2P=auto verifies peer content at every start. Recipe MIT; engine Apache-2.0; checkpoint under its own model-card licence.'
+max_context_len: 262144