MobileSAM (fastforks)

MobileSAM (Zhang et al. 2023, Kyung Hee University): Segment Anything with the ViT-H image encoder replaced by a TinyViT-5M (an MBConv stage, then window attention with depthwise convs) distilled from it; SAM's own prompt encoder and mask decoder, so points, boxes and mask logits work the same. The portable module() is the image encoder only.

This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/ChaoningZhang/MobileSAM at f706ad9c4eb7.

Task: promptable_segmentation. Tier: experimental. Outputs: pred_masks, iou_scores. Backends: portable, kernels.

Input: one image plus a point, box or text prompt. Output: masks with quality scores.

Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.

variant weights (author link) SHA-256 weights licence commercial use
mobile-sam@1 mobile_sam.pt 6dbb90523a35 Apache-2.0 yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0 AND MIT. Licence files: LICENSE, LICENSE-TinyViT.

Training data: image encoder distilled from SAM ViT-H on 1 % of SA-1B (about 100k images) per the README and paper; prompt encoder and mask decoder are SAM's (trained on SA-1B: 11M licensed images, 1.1B automatically generated masks); the dataset itself is under the SA-1B research licence.

Licence evidence: https://github.com/ChaoningZhang/MobileSAM/blob/f706ad9c4eb7f219c00d9050e46328518ffb65d2/LICENSE (Apache-2.0; weights/mobile_sam.pt is in the same tree and the README names no other terms); the same file from a co-author: https://huggingface.co/dhkim2810/MobileSAM/blob/4e2e5245fe9dc63096d575d36e70eb39b03b3aba/README.md (license: mit); TinyViT: https://github.com/microsoft/Cream/blob/4a13c4091e78f9abd2160e7e01c02e48c1cf8fb9/LICENSE

Input size

any H x W >= 1, resized inside to the fixed encoder input 1024x1024 (the default export size) Tested up to (portable, fp16, RTX 5060 Ti 16 GB): mobile-sam 1080x1920 (0.2 GiB peak allocated, 0.2 reserved)

Speed and memory

Promptable segmentation, synthetic, 1024x1024

model time (ms): original fp32 original portable kernels kernels speed-up: vs original vs portable peak memory (MiB, allocated / reserved): original portable kernels
mobile-sam 30.3 23.5 10.5 6.86 3.4x 1.5x 207 / 286 183 / 210 215 / 296

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
mobile-sam 0.21 0.71 1.60 1.01 0.47 0.29

torch.compile and TensorRT

model input time: portable compile TensorRT fp16 kernels preparation: compile (cold first call) ONNX + engine build peak MiB (alloc / reserved): portable compile kernels TensorRT (engine + torch)
mobile-sam 1024x1024 10.5 ms 6.22 ms 4.99 ms (image encoder only) 6.86 ms 25.5 s 60.9 s 183 / 210 203 / 232 215 / 296 219 / 252

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or (fp32) where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.

Accuracy

On public datasets

One point per ground-truth instance (the interior point farthest from the border); IoU of the best-scored of 3 masks / of the single mask. Original = the original code named under Details, same checkpoint and protocol.

variant dataset original fp32 original fp16 portable kernels note
mobile-sam COCO val2017, every 10th image, point prompts, mIoU best of 3 / single mask % 51.53 / 49.90 51.48 / 49.91 51.53 / 49.91 51.53 / 49.91

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 5eafe838+dirty, 2026-11-10.

Parity with the original code

Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.0013 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.81 % and p99 <= 4.1 % of the reference's median |value| (absolute error of the output pred_masks).

Usage

from fastforks import promptable_segmentation

model = promptable_segmentation.load("mobile-sam")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg", input_points=[[x, y]], input_labels=[1])
result.masks  # [M, H, W] bool
# SAM 3 (text prompts): model("photo.jpg", text="coin") -> boxes, scores, masks
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')

Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: mobile-sam.

Kernels backend

promptable_segmentation.load("mobile-sam", mode="kernels") runs our CUDA kernels (fvm_conv, fvm_extra, fvm_mb, fvm_r3). It needs a prebuilt kernel for your GPU architecture (downloaded from https://huggingface.co/fastforks/kernels on first use) and a recent NVIDIA driver; if there is none it raises BackendUnavailableError with the reason and never falls back silently. mode="auto" picks kernels when it can run and logs the choice.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including fastforks/mobile-sam