diff --git a/recipes/glm-5-3-flash-exl3-3-05bpw-on-1x-rtx-pro-6000-gpu-expert-cache-h/recipe.yaml b/recipes/glm-5-3-flash-exl3-3-05bpw-on-1x-rtx-pro-6000-gpu-expert-cache-h/recipe.yaml
index 8896df84d..9a80e9b5d 100644
--- a/recipes/glm-5-3-flash-exl3-3-05bpw-on-1x-rtx-pro-6000-gpu-expert-cache-h/recipe.yaml
+++ b/recipes/glm-5-3-flash-exl3-3-05bpw-on-1x-rtx-pro-6000-gpu-expert-cache-h/recipe.yaml
@@ -121,3 +121,5 @@ provenance:
     - 'https://github.com/SSHdotCodes/glm-5.3-flash-pro6000/blob/main/docs/exl3.md'
     - 'https://huggingface.co/turboderp/GLM-5.3-Flash-exl3/tree/3.05bpw'
   notes: "Submitted from the repo at bcc27a7587e0e22e5752b93534e47c7acedb9a1a (2026-10-09 18:06 -0400, 'Make EXL3 3.05bpw with a GPU expert cache the default runtime'). All performance figures are the author's own measurements from benchmarks/exl3-20261009/api-bench-exl3.json (verified verbatim at ingest); the 59/60 agent bench and KLD 0.0680 are from agent-bench-exl3.json and turboderp's model-card chart as documented in docs/exl3.md. Recipe + measurements by SSHdotCodes; EXL3 3.05bpw checkpoint by turboderp; TabbyAPI (theroyallab) run unmodified at a pinned commit, ExLlamaV3 stock 1.6.0 wheel - no engine patches, the cache is process-local pointer-table interception. Runtime replaces the same author's llama.cpp UD-IQ3_XXS recipe of 2026-09-20 (kept in docs/llamacpp.md). Fourth ExLlamaV3 recipe on site (after the 1x RTX 3090 RAM/NVMe tiering, 2x RTX 5090 hot-swap and 2x CMP 170HX entries) but FIRST on Blackwell, and first single-card GLM recipe in the 1x RTX PRO 6000 bucket (prior 6000-bucket GLM entries are NVFP4 4-card lanes). QFN sibling repo (qwen-3.8-flash-next-pro6000, SGLang) intentionally not ingested to avoid a 3rd 1x6000 QFN bucket entry."
+storage_requirements:
+  ram_gb: 128.0