Started mlx-vlm-server.
INFO: Started server process [72603]
INFO: Waiting for application startup.
2026-08-19 19:16:18,922 - INFO - Pre-loading language model: donedynamics/Qwen3.8-27B-heretic-VL-MLX-8bit
2026-08-19 19:16:18,926 - INFO - Loading model: donedynamics/Qwen3.8-27B-heretic-VL-MLX-8bit
2026-08-19 19:16:19,135 - INFO - HTTP Request: GET https://huggingface.co/api/models/donedynamics/Qwen3.8-27B-heretic-VL-MLX-8bit/revision/main "HTTP/1.1 200 OK"
Fetching 19 files: 0%| | 0/19 [00:00<?, ?it/s]
Fetching 19 files: 100%|██████████| 19/19 [00:00<00:00, 5790.71it/s]
2026-08-19 19:16:21,193 - INFO - Model and processor loaded successfully.
2026-08-19 19:16:21,193 - INFO - Language model ready, continuous batching enabled.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8080 (Press CTRL C to quit)
Stopping mlx-vlm-server...
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO: Application shutdown complete.
INFO: Finished server process [72603]
mlx-vlm-server stopped with status 143
Category
App interaction issue
What happened
No description provided.
Diagnostics
Environment
Model & server
Server output (last 18 lines)