Not runnable todaySegmentationVerified 2026-11-05
EfficientSAM ViT-S
yformer/EfficientSAM (efficient_sam_vits.pt)
EfficientSAM ViT-S is a image segmentation model (Apache-2.0). Not runnable on Mixpeek today.
Something blocks it today, such as the license, remote code or a GPU-only runtime. The reason is below.
No demo for EfficientSAM ViT-S yet
A video, image, slideshow or playground goes here once we record one on our own data.
What it is good and bad at
- Best at
- SAM-style point and box prompted masks at a fraction of SAM ViT-H cost (masked-image pretraining distillation).
- Worst at
- Images only (no video memory); below SAM 2 tiny in quality and tooling.
- Task
- Segmentation
- Input
- Image
- Output
- Masks, Scores
- Use cases
- Segmentation, Object detection
Templates that use it
No template uses this model yet. Browse templates.
Input and output
Input
- image
- resolution
- 1024x1024
- prompts
- points and boxes
Output
- masks
- binary masks with IoU predictions
How Mixpeek wires it
- Extractors
- None today
- Feature URIs
- None today
- Vector indexes
- None
- Retriever stages
- None
- Combines with
- detector boxes -> EfficientSAM masks -> masked crops -> SigLIP
How it runs
- Status
- Not runnable today Weights ship as .pt pickles (ViT-S zipped) and the model code lives in the GitHub repo; needs a safetensors conversion and a vendored model definition (or the repo's ONNX export) before it can be a plugin. SAM 2.1 tiny covers the same need with transformers support.
- Serve apps
- None
- Runtime
- repo build_efficient_sam_vits() / ONNX export
- Weights
- Pickle, no remote code
- Parameters
- Not recorded
- Size on disk
- Not recorded
- Preprocessing
- Resize to 1024, normalize.
- Postprocessing
- Threshold mask logits, pick by predicted IoU.
- Serving
- both
- Hardware
- Runs on CPU (slower without a GPU)
Scale to zero
- Minimum replicas
- 0
- Maximum replicas
- 1
- Idle timeout
- 600 s
- Memory
- 2 GB
- CPUs
- 2
- GPUs
- 0
- Cold start, node warm
- Not recorded
- Cold start, new node
- Not recorded
Measured cost
Unmeasured
No committed measurement; plan row 3 measures it in the standalone image.
Our evaluations
Unmeasured
We have not evaluated this model on our own data yet. Publisher results are in the sources below.
Questions
- What is EfficientSAM ViT-S best at?
- SAM-style point and box prompted masks at a fraction of SAM ViT-H cost (masked-image pretraining distillation).
- What are the limits of EfficientSAM ViT-S?
- Images only (no video memory); below SAM 2 tiny in quality and tooling.
- Can EfficientSAM ViT-S be used commercially?
- Yes. Apache-2.0 weights and code; no use restrictions.
- How does EfficientSAM ViT-S run on Mixpeek?
- Weights ship as .pt pickles (ViT-S zipped) and the model code lives in the GitHub repo; needs a safetensors conversion and a vendored model definition (or the repo's ONNX export) before it can be a plugin. SAM 2.1 tiny covers the same need with transformers support.