OLLAMA_NUM_PARALLEL may appear broken on Mac MLX models even when the setting is correct. Learn how to confirm serialization and fix the serving path.
Has OLLAMA_NUM_PARALLEL actually worked for you with Ollama’s MLX runner on Apple Silicon, or are your requests still getting queued?
Has OLLAMA_NUM_PARALLEL actually worked for you with Ollama’s MLX runner on Apple Silicon, or are your requests still getting queued?