start_server.sh

llama-server \
  -m ~/.cache/huggingface/hub/models--ggml-org--MiniCPM-V-4.6-GGUF/snapshots/1d73353fab60fe6040ab73eb1e457e2aab210100/MiniCPM-V-4.6-Q4_K_M.gguf \
  --mmproj ~/.cache/huggingface/hub/models--ggml-org--MiniCPM-V-4.6-GGUF/snapshots/1d73353fab60fe6040ab73eb1e457e2aab210100/mmproj-MiniCPM-V-4.6-bf16.gguf \
  --host 0.0.0.0 \
  --port 8080 \
  -ngl 99 \
  -n 1024 \
  -c 65536
  - verbosity 0