diff --git a/stacks/ollama.yml b/stacks/ollama.yml
index 9d0fd6f..3acdf94 100644
--- a/stacks/ollama.yml
+++ b/stacks/ollama.yml
@@ -22,6 +22,12 @@ services:
       - TZ=Europe/Amsterdam
       - NVIDIA_VISIBLE_DEVICES=all
       - NVIDIA_DRIVER_CAPABILITIES=all
+      # Process requests sequentially to avoid batch overflow panics
+      - OLLAMA_NUM_PARALLEL=1
+      # Keep models loaded in VRAM (don't unload after idle)
+      - OLLAMA_KEEP_ALIVE=-1
+      # Load multiple models concurrently (mistral-nemo + nomic-embed-text)
+      - OLLAMA_MAX_LOADED_MODELS=2
     deploy:
       resources:
         limits: