diff --git a/recipes/qwen3-8-flash-next-w4a16-int4ple-on-2x-modded-cmp-170hx-pp2-mtp3/recipe.yaml b/recipes/qwen3-8-flash-next-w4a16-int4ple-on-2x-modded-cmp-170hx-pp2-mtp3/recipe.yaml
index 638b40762..f17272a91 100644
--- a/recipes/qwen3-8-flash-next-w4a16-int4ple-on-2x-modded-cmp-170hx-pp2-mtp3/recipe.yaml
+++ b/recipes/qwen3-8-flash-next-w4a16-int4ple-on-2x-modded-cmp-170hx-pp2-mtp3/recipe.yaml
@@ -138,3 +138,4 @@ provenance:
     - 'https://github.com/michael-lgtm/qwen38-flash-next-cmp-overlay'
     - 'https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates'
   notes: "Community ingest of DUFRelic/qwen38-flash-next-recipe @ 25f97f3c (lar-scout GitHub sweep Oct 5, queued as t_dd357cb3; repo created 2026-10-05, 5 commits, README-licensed for reuse; patches and models remain with their upstream authors). Serve profile transcribed from README section 4 @ the pinned commit; benchmark numbers are the author's section 5 tables (median-of-3 methodology with isolation audit), logged claimed_by=submitter T0 — no run file. Hardware is 'modded CMP 170HX' (74-SM unlock + VBIOS + undervolt + BAR1 P2P) — mod stack documented in runtime notes and tags (modded-hardware, sm-unlock); profile linked is the existing cmp-170hx-x2 (same silicon, 64 GB x2). First 170hx recipe whose hardware mod stack is part of the recipe. KV cache runs BF16 despite the FP8KV suffix (pinned build rejects FP8 for Qwen4Exp QSA). Model license: qwen-community-1.0."
+max_context_len: 262144