Downloads · 30 days
14
29% of all-time downloads
vitpose-base-simple-mlx
nazarkozak/vitpose-base-simple-mlx
vitpose-base-simple-mlx is a keypoint detection model from nazarkozak. Use it for the keypoint detection task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
ViTPose (vitpose-base-simple) converted to MLX for on-device human pose estimation on Apple Silicon. Weights are float16.
All-time downloads
49
Public
Repo size
172 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors172 MB · 100%
At a glance
- Task
- Keypoint Detection
- Library
- mlx
- License
- apache-2.0
- Model type
- vitpose
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026
- SHA
- 8f0b20af
Base models
Model card
From the Hugging Face model README
ViTPose base-simple — MLX
ViTPose (vitpose-base-simple) converted to MLX for on-device human pose
estimation on Apple Silicon. Weights are float16.
Built for MLXPose — a native MLX Swift
ViTPose implementation. The Swift forward pass is numerically verified against the
Hugging Face reference (heatmaps max|Δ|=1.5e-6, decoded keypoints max 3e-5 px).
- Backbone: plain ViT-base (12 layers, dim 768), patch 16, input 256×192.
- Head: simple decoder → 17 COCO keypoint heatmaps (64×48).
- Conversion:
convert_vitpose_to_mlx.py.
Files
weights.safetensors— MLX float16 weights.config.json— original ViTPose config.
License
Apache-2.0. Pretrained weights derive from COCO/MPII training data — review dataset terms for your use case.
- Task
- Keypoint Detection
- Library
- mlx
- Type
- vitpose
- License
- apache-2.0
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026