Change model

Ran into an issue with the previous model for having mllama archetecture so I changed it
2026-06-26 08:36:45 -05:00
parent a971ff870f
commit 79edb6bb56
1 changed files with 1 additions and 1 deletions
@@ -25,7 +25,7 @@ That model is small enough to feel responsive on modest hardware, but still good
 If you want StepForge to send the screenshot itself to the model, pull a vision-capable model instead:

 ```bash
-ollama pull llama3.2-vision
+ollama pull gemma3
 ```

 That model can inspect pictures as well as text, so it is better when you want the AI to read the UI directly from the screenshot.