added README

2026-03-27 13:12:33 +00:00
parent 549f70b97a
commit 5647bc4336
2 changed files with 114 additions and 2 deletions
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -22,6 +22,6 @@ services:
    command: >
      --model /app/models/Qwen3.5-0.8B-UD-Q8_K_XL.gguf
      --quantization gguf
-      --gpu-memory-utilization 0.50
-      --max-model-len 4096
+      --gpu-memory-utilization 0.06
+      --max-model-len 32768
    restart: unless-stopped