diff --git a/recipes/qwen3-8-flash-next-w4a16-merlin-on-4x-rtx-3090-tp2xpp2-ep-mtp3-f/recipe.yaml b/recipes/qwen3-8-flash-next-w4a16-merlin-on-4x-rtx-3090-tp2xpp2-ep-mtp3-f/recipe.yaml
index 3d755af4d..e00533e4a 100644
--- a/recipes/qwen3-8-flash-next-w4a16-merlin-on-4x-rtx-3090-tp2xpp2-ep-mtp3-f/recipe.yaml
+++ b/recipes/qwen3-8-flash-next-w4a16-merlin-on-4x-rtx-3090-tp2xpp2-ep-mtp3-f/recipe.yaml
@@ -163,3 +163,7 @@ provenance:
     - 'https://github.com/halt95/qwen38-flash-next-3090s/blob/28cbb7293f134c244b443fb43bbf6e74ff4d8e24/README.md'
     - 'https://github.com/halt95/qwen38-flash-next-3090s/blob/28cbb7293f134c244b443fb43bbf6e74ff4d8e24/benchmarks/2026-10-06/BENCH-CARD.md'
   notes: "Community ingest of halt95/qwen38-flash-next-3090s @ 28cbb7293f134c244b443fb43bbf6e74ff4d8e24, release v2.5.1 (owner-named by Casey Oct 6; repo pushed 2026-10-06; Apache-2.0 + Qwen Community 1.0 for weights). Launch argv transcribed verbatim from scripts/serve-v2.5.sh @ 28cbb72 (selector-off legacy path, token-level checked against the raw script before POST); env exports verbatim from the same script. Perf numbers are the maintainer's 2026-10-06 bench card, logged claimed_by=submitter T0. Credits per the repo's own Credits section: Qwen (base), Intel AutoRound + RadixArk (quant components), DominikBucko (MTP packing), peakcrosser7 Flash-Next branch behind vLLM PRs #53896/#53899, aikitoria open-kernel-module P2P patch. Sibling repo halt95/Swift1.5-qwen38-flash-next-3090s is a post-train variant — NOT in scope this wave."
+max_context_len: 262144
+kv_pool_tokens: 924993
+storage_requirements:
+  ram_gb: 96.0