diff --git a/recipes/qwen3-8-flash-next-w4a16-fp8ple-on-2x-rtx-3090-tp2-expert-offloa/recipe.yaml b/recipes/qwen3-8-flash-next-w4a16-fp8ple-on-2x-rtx-3090-tp2-expert-offloa/recipe.yaml
index 01d8ffdb3..5e0fd674c 100644
--- a/recipes/qwen3-8-flash-next-w4a16-fp8ple-on-2x-rtx-3090-tp2-expert-offloa/recipe.yaml
+++ b/recipes/qwen3-8-flash-next-w4a16-fp8ple-on-2x-rtx-3090-tp2-expert-offloa/recipe.yaml
@@ -152,3 +152,6 @@ provenance:
     - 'https://github.com/DominikBucko/qwen38-flash-next-2x3090'
     - 'https://github.com/DominikBucko/qwen38-flash-next-2x3090/blob/939905b0dab8c6eb3852ff35cbbd42d098af2451/README.md'
   notes: "Community ingest of DominikBucko/qwen38-flash-next-2x3090 @ 939905b0dab8c6eb3852ff35cbbd42d098af2451 (owner-named by Casey Oct 6; 108 stars; last push 2026-10-02, Apache-2.0). Launch argv transcribed verbatim from scripts/serve-container.sh @ 939905b with configs/2x3090-128gb.env defaults inlined (128 GB headline profile); env exports verbatim from the same script. Token-level check done against the raw script before POST. Perf numbers are the author's README tables, logged claimed_by=submitter T0. Credits per repo repro.lock/THIRD_PARTY_NOTICES: checkpoint = Intel AutoRound target + RadixArk FP8 PLE + compact INT4 MTP, published by albucino."
+max_context_len: 262144
+storage_requirements:
+  ram_gb: 128.0