Download README.md from fastforks/mobile-sam: direct link, hf CLI and curl.
- Browser
- Download file 6.53 kB
-
https://huggingface.co/fastforks/mobile-sam/resolve/main/README.md
- Command line
-
hf download hf://fastforks/mobile-sam/README.md
-
curl -L -o README.md https://huggingface.co/fastforks/mobile-sam/resolve/main/README.md
library_name: fastforks
pipeline_tag: mask-generation
license: apache-2.0
tags:
- promptable_segmentation
- segment-anything
- promptable-segmentation
- cuda
- pytorch
- fastforks
- fastforks-card
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.