sam3-mlx
Segment images from text and geometric prompts with an unofficial native MLX port of SAM 3.
Text prompts “person” and “helmet” → masks on a real photograph.
| Input | Output |
|---|---|
| Image + text, boxes or points | Masks, boxes and confidence scores |
Apple Silicon · Metal · Python 3.13+ · uv
Quick start
uv venv --python 3.13
source .venv/bin/activate
uv pip install sam3-mlx
Weights download automatically; Hugging Face access to the official checkpoint is required.
from sam3_mlx import build_sam3_image_model
from sam3_mlx.model.sam3_image_processor import Sam3Processor
model = build_sam3_image_model()
processor = Sam3Processor(model, resolution=1008)
state = processor.set_image("image.jpg")
state = processor.set_text_prompt("shoe", state)
masks, boxes, scores = state["masks"], state["boxes"], state["scores"]
Use a resolution divisible by 14. Selected-frame video runs each frame independently; temporal tracking and SAM 3.1 are experimental.
License
SAM License; see LICENSE and third-party notices. Unofficial port; not affiliated with Meta. Official checkpoints have separate access terms.
For research and education. Outputs require human review.
2 maintainers
Metadata
2 maintainers
Release files for sam3-mlx 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| sam3_mlx-0.1.5.tar.gz | 1.9 MB | Without provenance | Details for sam3_mlx-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| sam3_mlx-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for sam3_mlx-0.1.5-py3-none-any.whl |
Total release size: 3.8 MB
Release files / sam3_mlx-0.1.5.tar.gz
| Download URL | sam3_mlx-0.1.5.tar.gz |
|---|---|
| Size | 1.9 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
83d51fecc31a5352d2a2b6388afb7c0cbca07d27d89f44479900a68d0af27436
|
|
BLAKE2b-256 checksum How to use checksums |
3ae7e61357b5fe28859d3d9f8603d5afafe90ff205696fe7cba9260c701a8950
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Release files / sam3_mlx-0.1.5-py3-none-any.whl
| Download URL | sam3_mlx-0.1.5-py3-none-any.whl |
|---|---|
| Size | 1.9 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7b5cda5c357654f44a3c1548944d35cefe296eb6751751e22427efa0d212866c
|
|
BLAKE2b-256 checksum How to use checksums |
8d45548c3e2994f88270784e271b4c995ef98170c87d4caeaa353db475438be4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Security for sam3-mlx 0.1.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
