Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

Search Fits in Task Vendor Quantisation Sort

8 builds · clear filters

YOLO26x-OptiQ-6bit

from Ultralytics/YOLO26

6-bit

Object detection · Ultralytics ↓ 188 · ♥ 4

Params

—

Weights

—

Mac memory

—

agpl-3.0 · updated 2026-09-28

YOLO26n-OptiQ-6bit

from Ultralytics/YOLO26

6-bit

Object detection · Ultralytics ↓ 57 · ♥ 0

Params

—

Weights

—

Mac memory

—

agpl-3.0 · updated 2026-09-28

YOLO26m-OptiQ-6bit

from Ultralytics/YOLO26

6-bit

Object detection · Ultralytics ↓ 36 · ♥ 0

Params

—

Weights

—

Mac memory

—

agpl-3.0 · updated 2026-09-28

YOLO26l-OptiQ-6bit

from Ultralytics/YOLO26

6-bit

Object detection · Ultralytics ↓ 29 · ♥ 0

Params

—

Weights

—

Mac memory

—

agpl-3.0 · updated 2026-09-28

docling-layout-heron-101-mlx-bf16

from docling-project/docling-layout-heron-101

bf16

Object detection · docling-project ↓ 25 · ♥ 1

Params

77M

Weights

≈ 153 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-05-17

rfdetr-base-fp32

from roboflow/rf-detr

fp32

Object detection · roboflow ↓ 25 · ♥ 0

Params

32M

Weights

≈ 129 MB

Mac memory

8 GB+

updated 2026-03-31

YOLO26s-OptiQ-6bit

from Ultralytics/YOLO26

6-bit

Object detection · Ultralytics ↓ 24 · ♥ 0

Params

—

Weights

—

Mac memory

—

agpl-3.0 · updated 2026-09-28

docling-layout-heron-mlx-bf16

from docling-project/docling-layout-heron

bf16

Object detection · docling-project ↓ 21 · ♥ 0

Params

43M

Weights

≈ 86 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-05-17