diff --git a/recipes/mimo-v2-6-flash-rl-omni-on-4x-cmp-170hx-pp4-official-fp8-three-t/recipe.yaml b/recipes/mimo-v2-6-flash-rl-omni-on-4x-cmp-170hx-pp4-official-fp8-three-t/recipe.yaml
index 2da29351e..ac7293fc0 100644
--- a/recipes/mimo-v2-6-flash-rl-omni-on-4x-cmp-170hx-pp4-official-fp8-three-t/recipe.yaml
+++ b/recipes/mimo-v2-6-flash-rl-omni-on-4x-cmp-170hx-pp4-official-fp8-three-t/recipe.yaml
@@ -195,3 +195,7 @@ provenance:
     - 'https://github.com/kaka86mm/vllm-mimo-170hx/blob/f9f8d73087c8828128975cbf8db7b32aa1398aa1/scripts/launch-official-v33.sh'
     - 'https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL'
   notes: "Community ingest of kaka86mm's recipe repo @ f9f8d73 (repo owner-named by Casey Oct 6 as part of the 170HX focus wave; MIT LICENSE in repo). Launch argv + runtime env transcribed verbatim from scripts/launch-official-v33.sh @ f9f8d73 (v3.3 production; the v3.0 form launch-official.sh adds patch bind-mounts). Measured numbers are the author's README results tables (2026-09/10 measurement campaign incl. the 2026-10-04 re-measure), logged claimed_by=submitter T0 (no run file). Model is omni-modal (text/image/video/audio in, tool calls, reasoning parser) per the repo README + docs/RESULT.md verification records; the official checkpoint ships a hidden 2048-token output cap the download script rewrites to 65536. Built-on credits per the repo's own Credits section: wtdcode/vllm-backport (sm80 fork), avtc PR#106 (official-checkpoint sharding/MTP/Marlin fixes), upstream vLLM #58235 (ViT sink fix), LMCache PR#4410 (CPU/disk KV tiers), vllm#59673 (QK-dot split ported in v3.3)."
+max_context_len: 1048576
+kv_pool_tokens: 2061355
+storage_requirements:
+  ram_gb: 64.0