diff --git a/recipes/glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw/recipe.yaml b/recipes/glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw/recipe.yaml
index 2ab5e5df2..91b482a4d 100644
--- a/recipes/glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw/recipe.yaml
+++ b/recipes/glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw/recipe.yaml
@@ -151,3 +151,6 @@ provenance:
     - 'https://github.com/adrienbrault/glm5.3-flash-2x-rtx5090/blob/main/scripts/FLAG-DECISIONS.txt'
     - 'https://github.com/adrienbrault/glm5.3-flash-2x-rtx5090/blob/main/bench/results/r927-glm53-dflash-window.md'
   notes: "Submitted from the repo at 4e3e0f0f5bfbcf1f963936da89b6a80cda2876b8 (2026-10-09 00:45 +0200). All figures are the author's own measurements (bench/results R927 served arm B-D with R915c/R925 spread arms, R924 prefill arm, R900 memory layout; raw records in bench/results/<date>-<round>/). Hardware note: 60 GB usable of 2x32 GB DDR5-6000 hosts the CPU-offloaded routed experts (26.4 GiB) plus the pinned vision tower. Exact-output claim per author: no expert skipped, every drafted token verified; greedy run-to-run instability documented (R916) with opt-in deterministic flags. First TabbyAPI-served and first RTX-5090 recipe on the site; second ExLlamaV3 entry after Flun's 2x CMP 170HX."
+kv_pool_tokens: 262144
+storage_requirements:
+  ram_gb: 64.0