diff --git a/hw/dixie/default.nix b/hw/dixie/default.nix
index 3ef26eb..2fbdb1e 100644
--- a/hw/dixie/default.nix
+++ b/hw/dixie/default.nix
@@ -51,9 +51,14 @@ let
     model = ${modelsDir}/qwen3-embedding-0.6b/Qwen3-Embedding-0.6B-Q8_0.gguf
     embedding = true
     pooling = cls
+    ; A whole input must fit in one physical batch AND one slot. batch-size defaults to 2048
+    ; and silently caps ubatch, and ctx is split across slots, so both were 2048 in practice:
+    ; Honcho's longer messages (up to its 8192-token EMBEDDING.MAX_INPUT_TOKENS) failed with
+    ; "input is too large to process". Size all three to 8192 per slot.
+    batch-size = 8192
     ubatch-size = 8192
-    ctx-size = 8192
-    parallel = 4
+    ctx-size = 16384
+    parallel = 2
   '';
 
   # Vision (auxiliary.vision for all agents): its own server on :11433, loaded on first