MotionBricks G1 GGML needs about 0.6 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB to 0.5 GB.
MotionBricks G1 GGML – a lightweight pose and style model for NVIDIA MotionBricks G1.
MotionBricks G1 GGML is a native F32 GGML/GGUF conversion of NVIDIA MotionBricks' released G1 pose, root, and VQ‑decoder checkpoints, plus 15 style primitives. The bundle contains 183,148,382 learned F32 parameters and targets the 34‑joint Unitree G1 skeleton.
Good at
- Pose estimation for the G1 skeleton
- Style transfer with 15 primitives
- CPU and Vulkan inference via motion-bricks.cpp
Limits
- No vision support
- License requires NVIDIA Open Model License compliance
- No mixture of experts
Best for
- Embedded robotics control
- Real‑time pose generation on CPUs
- Vulkan‑based inference on GPUs
Who it’s for. Engineers and researchers working with NVIDIA MotionBricks G1 who need a GGML/GGUF conversion for local inference. The model is suitable for developers building robotics applications that require pose and style generation on edge devices.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.6 GB | Fits | Get file → | |
| — | 0.1 GB | 0.7 GB | Fits | Get file → | |
| — | 0.5 GB | 1.1 GB | Fits | Get file → |
For an 8 GB VRAM budget, the 0.05 GB file with 0.6 GB memory at 8 k context is suitable. For 4 GB VRAM, use the 0.05 GB file. For larger memory, the 0.55 GB file uses 1.1 GB at 8 k context. Estimates are approximate.
What GPU do you need for MotionBricks G1 GGML?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
Which MotionBricks G1 GGML quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MotionBricks G1 GGML
How much VRAM does MotionBricks G1 GGML need?
About 0.6 GB at its main file with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run MotionBricks G1 GGML on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MotionBricks G1 GGML GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.1 GB, file is 0.5 GB.
Where can I download MotionBricks G1 GGML GGUF?
The files are on Hugging Face in the LocalAI-io/MotionBricks-G1-GGML repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MotionBricks G1 GGML use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MotionBricks G1 GGML on 8 GB VRAM?
Yes, the 0.05 GB quant file uses about 0.6 GB memory at 8 k context, fitting within 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision support.
What license applies to this conversion?
The conversion remains subject to NVIDIA Open Model License and requires attribution as per NOTICE.