diff --git a/stacks/llm/llama-swap-config.yaml b/stacks/llm/llama-swap-config.yaml
index d8caee7..1b1daec 100644
--- a/stacks/llm/llama-swap-config.yaml
+++ b/stacks/llm/llama-swap-config.yaml
@@ -15,7 +15,9 @@ healthCheckTimeout: 300
 logLevel: info
 
 macros:
-  common: "-ngl 99 --parallel 1 --ctx-size 65536 --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0"
+  # --jinja applies each model's embedded chat template (REQUIRED for gpt-oss'
+  # harmony format, else content comes back empty; harmless/correct for gemma4).
+  common: "-ngl 99 --parallel 1 --ctx-size 65536 --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0 --jinja"
 
 models:
   "gpt-oss-20b":