rob-laz/sam3-gguf

Model

0

stars

1

commits

3

linked in READMEs

Mar 24, 2026

updated

ggml
gguf
grounding
image-segmentation
sam3
segmentation
vision
Browse cluster: Semantic Segmentation with SegFormer

README

SAM3-GGUF

GGUF weights for SAM 3 (Segment Anything Model 3), converted for use with sam3.cpp.

Available Variants

FilePrecisionSizeInference (M4 Max)
sam3-image-f32.ggufF323.2 GB3.5s
sam3-image-f16.ggufF161.7 GB3.5s
sam3-image-q8_0.ggufQ8_01.0 GB3.2s

Usage

import sam3cpp

model = sam3cpp.Sam3Model("hf://rob-laz/sam3-gguf/sam3-image-f16.gguf")
pred = model.predict("photo.jpg", "person")
print(f"{pred.count} detections")

See sam3.cpp for build instructions and full documentation.

Conversion

Converted from the original SAM 3 MLX weights using tools/convert_mlx_sam3_to_gguf.py.

Contributors

rob-laz

1 commits

rob-laz/sam3-gguf

Model

0

stars

1

commits

3

linked in READMEs

Mar 24, 2026

updated

ggml
gguf
grounding
image-segmentation
sam3
segmentation
vision
Browse cluster: Semantic Segmentation with SegFormer

README

SAM3-GGUF

GGUF weights for SAM 3 (Segment Anything Model 3), converted for use with sam3.cpp.

Available Variants

FilePrecisionSizeInference (M4 Max)
sam3-image-f32.ggufF323.2 GB3.5s
sam3-image-f16.ggufF161.7 GB3.5s
sam3-image-q8_0.ggufQ8_01.0 GB3.2s

Usage

import sam3cpp

model = sam3cpp.Sam3Model("hf://rob-laz/sam3-gguf/sam3-image-f16.gguf")
pred = model.predict("photo.jpg", "person")
print(f"{pred.count} detections")

See sam3.cpp for build instructions and full documentation.

Conversion

Converted from the original SAM 3 MLX weights using tools/convert_mlx_sam3_to_gguf.py.

Contributors

rob-laz

1 commits