diff --git a/scripts/frank-large.env b/scripts/frank-large.env
index 05dab9e..256f893 100644
--- a/scripts/frank-large.env
+++ b/scripts/frank-large.env
@@ -72,6 +72,9 @@ FRANK_LARGE_PUBLISH=7770:7770
 FRANK_LARGE_MAXLEN=262144
 FRANK_LARGE_SEQS=4
 FRANK_LARGE_UTIL=0.45
+# First-deploy boot (2026-10-01): GPU KV cache size 819,332 tokens,
+# Maximum concurrency for 262,144 tokens per request 3.13x; healthy at 230 s.
+# Change MAXLEN/SEQS/UTIL or the image and this line moves — re-read it.
 
 # --- speculative decode: cross-model MTP (measured +51% decode) ---------------
 # mtp beats dflash here (19.8 vs 17.4 t/s) and needs 2 draft tokens, not 8:
diff --git a/serverAppConfigs-docs/LLM/frank-large-vllm-mimo-v26-bf16.md b/serverAppConfigs-docs/LLM/frank-large-vllm-mimo-v26-bf16.md
index cef2dec..fa1b71b 100644
--- a/serverAppConfigs-docs/LLM/frank-large-vllm-mimo-v26-bf16.md
+++ b/serverAppConfigs-docs/LLM/frank-large-vllm-mimo-v26-bf16.md
@@ -155,8 +155,13 @@ chase text drift between spec and no-spec arms as a regression.
   frank-primary lesson).
 - Bench windows: `systemctl stop frank-large` is enough (mask fails on the
   relinked unit; the deploy restores).
-- First-deploy fact to record here: the boot-time KV pool line
-  (`Maximum concurrency for 262,144 tokens per prompt: N.Nx`).
+- First-deploy facts (2026-10-01, deploy #3): healthy after **230 s**;
+  boot log `GPU KV cache size: 819,332 tokens, Maximum concurrency for
+  262,144 tokens per request: 3.13x` — four sessions share the pool
+  (the scheduler, not a carve). Live battery green: alias `frank-large`,
+  reasoning split into `reasoning`, tool_calls with correct args, and
+  `/metrics` acceptance pos0 69% pos1 44% (54/86 draft tokens accepted),
+  matching the bench window.
 
 ## Rollback