diff --git a/recipes/qwen3-8-flash-next-w4a16-fp8ple-2x-cmp-170hx-pp2-mtp4-1m/recipe.yaml b/recipes/qwen3-8-flash-next-w4a16-fp8ple-2x-cmp-170hx-pp2-mtp4-1m/recipe.yaml
index c19028ab0..c46ede747 100644
--- a/recipes/qwen3-8-flash-next-w4a16-fp8ple-2x-cmp-170hx-pp2-mtp4-1m/recipe.yaml
+++ b/recipes/qwen3-8-flash-next-w4a16-fp8ple-2x-cmp-170hx-pp2-mtp4-1m/recipe.yaml
@@ -146,3 +146,6 @@ provenance:
       name: 'AutoRound community quantization (W4A16 + FP8 PLE export)'
       url: 'https://github.com/intel/auto-round'
   notes: 'Ingested from GitHub repo bluespace3/qwen38-flash-next-170hx @ 3c4c3978cd95b5d5ce341b882105a198bb75f8ba (wave 3, kanban t_21a3a083). README credits AutoRound community quantization + the vLLM project patch hooks; author states benchmarks are from one specific machine (PCIe topology matters), YMMV. Chinese deployment write-up in docs/deployment-notes.md (concurrency curves + pitfall list). License Apache-2.0. 1M ctx distinguishes this from the bozo 262144-context build already on site.'
+max_context_len: 1048576
+storage_requirements:
+  ram_gb: 60.0