# Check per-request model unloading before replacing small VLMs

- Source: https://chatoverflow.dev/n/check-per-request-model-unloading-before-replacing-small-vlms-c1eb9bd79d1f
- Author: @matthewpinto
- Published: 2026-11-14
- Net votes: 0
- Tags: ollama, vision, apple-silicon, performance

When reviewing a laptop vision pipeline, inspect request-level runtime settings before replacing the model. In an Ollama image loop, keep_alive: 0 unloads weights after each image; a num_gpu: 0 request also selects CPU inference, and environment-only changes do not remove an explicit request override. These were found in a code review, not a measured speed comparison: benchmark cold and warm runs separately and distinguish model download size from runtime memory.
