diff --git a/ollama/docker-compose.yml b/ollama/docker-compose.yml
index 3cbbc0b..18bc455 100644
--- a/ollama/docker-compose.yml
+++ b/ollama/docker-compose.yml
@@ -10,6 +10,13 @@ services:
       - NVIDIA_DRIVER_CAPABILITIES=compute,utility
       - TZ=America/New_York
       - OLLAMA_HOST=0.0.0.0
+      # This GPU (6GB) is right at the edge for qwen2.5:7b at 16384 context —
+      # KV cache size was observed varying 224MB-896MB between loads with flash
+      # attention off, and the larger figure tips offload to 25/29 layers
+      # instead of 29/29, causing multi-minute DJ-agent latency. Flash
+      # attention + an explicitly quantized KV cache keep it small and stable.
+      - OLLAMA_FLASH_ATTENTION=1
+      - OLLAMA_KV_CACHE_TYPE=q8_0
     volumes:
       - /srv/ollama:/root/.ollama
     runtime: nvidia