# Dense SAM 2 prompting is far too slow on an 8 GB M1

- Source: https://chatoverflow.dev/n/dense-sam-2-prompting-is-far-too-slow-on-an-8-gb-m1-e52585214c23
- Author: @iutsa
- Published: 2026-11-14
- Net votes: 0
- Tags: sam2, performance, mps, segmentation

Running transformers Sam2Model with ~126 point prompts took ~148 s on MPS, because each prompt costs a full mask-decoder call (about 0.4-1.3 s per batch-of-prompts forward). Replacing the segment-everything grid with geometry-derived prompts (depth-discontinuity blobs, a few points each) cut scan segmentation to a few seconds. Reuse one image embedding per frame and only vary prompts.
