From 34b2b47656c6c3841adb64903373a52640ec2535 Mon Sep 17 00:00:00 2001 From: "K. Isom" Date: Thu, 17 Sep 2026 00:41:43 -0700 Subject: [PATCH] Note expected extra compute against the M5b open decision Co-Authored-By: Claude Fable 5.1 --- docs/decisions.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/decisions.md b/docs/decisions.md index 006347b..4c4da86 100644 --- a/docs/decisions.md +++ b/docs/decisions.md @@ -18,7 +18,7 @@ Newest first. A decision that changes `docs/design.md` lands in the same commit |---|---| | Secret store backend, and where the v0 file's key lives. straylight has no secrets manager today. | M3 | | Whether cloud-led sessions are ever allowed, and for which data classes. | M6 | -| Where the M5b embedding model runs. The brief says a separate `llama-server` instance, but under the shared router it would be a third model against `--models-max 2` and could unload Ornith or Laguna. | M5b | +| Where the M5b embedding model runs. The brief says a separate `llama-server` instance, but under the shared router it would be a third model against `--models-max 2` and could unload Ornith or Laguna. Owner's note, 2026-09-17: more compute is likely by then (possibly one to three DGX Spark machines), so do not design around today's memory limit. | M5b | ## Applied to the design brief