Downloads · 30 days
2.5K
100% of all-time downloads
MotionBricks-G1-GGML
LocalAI-io/MotionBricks-G1-GGML
MotionBricks-G1-GGML is a machine learning model from LocalAI-io. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for ggml. The card lists the license as other.
Native F32 GGML/GGUF conversion of NVIDIA MotionBricks' released G1 pose, root, and VQ-decoder checkpoints, plus the 15 released style primitives. It is produced by motion-bricks.cpp for CPU and Vulkan inference.
All-time downloads
2.5K
Public
Repo size
733 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf733 MB · 100%
At a glance
- Library
- ggml
- License
- other
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026
- SHA
- cc2a4760
Model card
From the Hugging Face model README
MotionBricks-G1-GGML
Native F32 GGML/GGUF conversion of NVIDIA MotionBricks' released G1 pose,
root, and VQ-decoder checkpoints, plus the 15 released style primitives. It is
produced by
motion-bricks.cpp for CPU and
Vulkan inference.
NVIDIA currently publishes MotionBricks through Git LFS rather than a separate
Hugging Face model repository. This conversion is linked to the pinned
NVlabs/GR00T-WholeBodyControl revision.
Install the complete checked bundle at generated/g1-f32 and
generated/styles with:
python scripts/download_gguf_weights.py
MANIFEST.json and SHA256SUMS record the source revision, exact paths,
sizes, and SHA-256 hashes. The bundle contains 183,148,382 learned F32
parameters and targets MotionBricks' released 34-joint Unitree G1 skeleton.
License and provenance
The original checkpoints and this converted representation remain subject to
the NVIDIA Open Model License in UPSTREAM_LICENSE. Redistribution requires
retaining that agreement and NVIDIA's attribution in NOTICE. This conversion
grants no additional rights. Use is also subject to NVIDIA's Trustworthy AI
and trade-compliance terms described by that agreement.
- Library
- ggml
- License
- other
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026