diff --git a/recipes/glm-5-3-flash-exl3-3-05bpw-on-2x-rtx-3090-vllm-exllamav3-cpu-exp/recipe.yaml b/recipes/glm-5-3-flash-exl3-3-05bpw-on-2x-rtx-3090-vllm-exllamav3-cpu-exp/recipe.yaml
index 1d4e1fd35..c807eb1b1 100644
--- a/recipes/glm-5-3-flash-exl3-3-05bpw-on-2x-rtx-3090-vllm-exllamav3-cpu-exp/recipe.yaml
+++ b/recipes/glm-5-3-flash-exl3-3-05bpw-on-2x-rtx-3090-vllm-exllamav3-cpu-exp/recipe.yaml
@@ -170,3 +170,6 @@ provenance:
     - 'https://github.com/DominikBucko/glm53-flash-2x3090/blob/main/benchmarks/2026-10-12/summary.json'
     - 'https://github.com/DominikBucko/glm53-flash-2x3090/blob/main/repro.lock.json'
   notes: "Ingested by localai-recipes from the public launch-repro repo @ 597920a (Apache-2.0, created+pushed 2026-10-12): launch-repro docker runtime with checksummed overlays, repro.lock.json, in-repo benchmark report (benchmarks/2026-10-12, release_image_validation: kv_cache_tokens 264160, ~21.4 GiB/GPU after load). Performance rows transcribed verbatim from benchmarks/2026-10-12/summary.json measured_runs (best of 2 per shape; both runs' decode ranges kept in notes). Same turboderp 3.05bpw weights pin shared by the site's Flun/SSHdotCodes/sybil GLM EXL3 recipes. Distinct from held saitakarcesme/glm5.3-flash-2x3090 (glm53-flash-offload ExLlamaV3-native stack, ~30 tok/s) — that hold was repo-specific and remains held."
+max_context_len: 262144
+storage_requirements:
+  ram_gb: 128.0