Does NotchDock monitor Ollama or LM Studio?
No. NotchDock does not currently provide an Ollama or LM Studio integration, an LLM telemetry setting, or a notch display for token speed, GPU use, VRAM, or thermal state.
See which Ollama models are running
In Terminal, run ollama ps to list currently running models. Run ollama ls to list models available locally, or ollama run MODEL to start a model. These commands are documented in the Ollama CLI reference.
Inspect generation metrics
For API calls, Ollama documents response fields such as prompt token count, generated token count, and timing durations. A non-streaming /api/generate response includes usage fields; for streaming, the metrics arrive in the final chunk. See Ollama’s API usage documentation.
These are Ollama’s model and request metrics. They do not by themselves establish whole-system GPU utilization or memory use. For broader process and system views, use macOS Activity Monitor and consult Apple’s Activity Monitor User Guide.
What NotchDock can do
NotchDock has a sports tracker and other Mac notch utilities. See the sports tracker details. This page makes no claim that a local AI integration is available.