diff --git a/app/priv/blog/engineering/2026/05-14-generate-an-init-script-to-get-your-team-up-and-running.md b/app/priv/blog/engineering/2026/05-14-generate-an-init-script-to-get-your-team-up-and-running.md
index 1997585..bdba153 100644
--- a/app/priv/blog/engineering/2026/05-14-generate-an-init-script-to-get-your-team-up-and-running.md
+++ b/app/priv/blog/engineering/2026/05-14-generate-an-init-script-to-get-your-team-up-and-running.md
@@ -64,9 +64,9 @@ According to the agent:
 
 It ends with a summary showing how to start the server (port 8056), demo credentials, and handy make commands.                                                                                                                                                  
 
-The snippet below is from my performance widget. Token generation is not super fast, but all 32 turns ran while attending Chris Parsons’ webinar. 2.5 minutes for a script that ’just works’ is good enough for me.
+The snippet below is from my performance widget. Token generation is not super fast, but all 32 turns ran while attending Chris Parsons' webinar. 2.5 minutes for a script that _just works_; is good enough for me.
 
-📊 Performance: llama.cpp/Qwen3.6-35B-A3B-MXFP4<sub>MOE.gguf</sub>                                                                                                                                                                                                     
+📊 Performance: llama.cpp/Qwen3.6-35B-A3B-MXFP4-MOE.gguf                                                                                                                                                                                                     
   Prefill: 28,376 tokens @ 5253.8 tok/s
   Generation: 5,699 tokens @ 38.8 tok/s
   Combined: 34,075 tokens @ 223.5 tok/s (2.5m total)