Skip to content
Search models or paste a model link. Press Enter to search.

SAM 3

facebook/sam3
Left and right arrow keys switch the vendor.
Embedl-optimized · TensorRT
facebook/sam3 architecture graph
facebook/sam3 architecture graph
  • huggingface
  • INT8
  • Orin NX 16GB
Labels
  • Image
  • Text
  • Segmentation
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 10.16.2.10 with Embedl optimizations
Input size
924×924 image, text prompt up to 32 tokens
Output
Masks, boxes and scores
Run SAM 3 on Orin NX 16GB

Meta's SAM 3 finds every object a short text prompt names in a photo, such as "yellow school bus", and returns a mask, box and score for each one.

Methodology

  • Latency: batch 1, one photo and prompt. GPU compute: the engine alone between CUDA events, copies excluded, mean over 20 s after a 5 s warm-up. Median latency: the served request end to end (tokenizing, resizing to 924×924, the engine, masks to PNG at the photo's size), median of 10 on one 640×480 COCO photo.
  • Accuracy: COCO mask mAP (IoU 0.50 to 0.95), with mAP@50 and mAP@75, on the first 300 val2017 images with objects, each category present prompted by its name, through the served model's own pre- and post-processing. Only categories present are prompted, so the numbers compare builds and are not SAM 3's published results.
  • Memory: peak resident memory of the server, engine loaded and one request answered (on Jetson, GPU memory is system memory).
  • Size: the TensorRT engine.
  • Baseline FP32: the unquantized SAM 3 in FP32 in onnxruntime, on the same images and prompts, for accuracy; its ONNX weights, for size. There is no FP16 baseline yet: TensorRT's FP16 build of the unquantized model finds nothing (mask mAP 0.0) because its values overflow FP16, and a valid one needs mixed precision. Latency is not compared until then.

Files

Image Size

Model

docker.io/embedl/models:hf.facebook.sam3.int8-embedl.orin-nx-16gb.2026111322534ff1

—

Runtime

docker.io/embedl/models:runtimes.tensorrt.arm64.20261110110630a2

—