Kimodo-SOMA-SEED-v1.1 needs about 1.8 GB of memory at F32 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Kimodo-SOMA-SEED-v1.1: 3D skeletal motion generation from text and constraints
Kimodo-SOMA-SEED-v1.1 is a diffusion model that generates 30‑joint 3D skeletal animations from text prompts and pose constraints. It is built on a two‑stage transformer and uses a Llama‑derived text encoder. The model is ready for commercial use under the NVIDIA Open Model License.
Good at
- Text‑driven motion generation
- Constraint‑based pose control
- Low‑error constraint following
Limits
- Requires 1.8 GB VRAM at 8 k context
- No vision or audio input
- Only 30‑joint SOMA skeleton
Best for
- Creating humanoid robot demonstrations
- Generating synthetic human motion data
- Animating game characters
Who it’s for. Developers and researchers needing controllable 3D human motion. Suitable for animation, robotics, and synthetic data pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F32 | 1.1 GB | 1.8 GB | Fits | Get file → |
The only available quant is F32, 1.13 GB file size. It requires approximately 1.8 GB VRAM at 8 k context. No other quantizations are provided, so use the F32 model if your GPU can accommodate the memory estimate.
What GPU do you need for Kimodo-SOMA-SEED-v1.1?
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 F32 (1.1 GB file, about 1.8 GB in use).
Which Kimodo-SOMA-SEED-v1.1 quant should you choose?
F32 (1.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kimodo-SOMA-SEED-v1.1
How much VRAM does Kimodo-SOMA-SEED-v1.1 need?
About 1.8 GB at F32 with an 8K context window. That is the 1.1 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 Kimodo-SOMA-SEED-v1.1 on an 8 GB GPU?
Yes, with F32: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kimodo-SOMA-SEED-v1.1 GGUF?
It depends on the quant: F32 is 1.1 GB.
Where can I download Kimodo-SOMA-SEED-v1.1 GGUF?
The files are on Hugging Face in the LocalAI-io/Kimodo-SOMA-SEED-v1.1-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 Kimodo-SOMA-SEED-v1.1 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 Kimodo-SOMA-SEED-v1.1 on 8 GB VRAM?
The model needs about 1.8 GB VRAM at 8 k context, so it fits within 8 GB. However, additional VRAM may be required for the text encoder and runtime overhead.
Does the model support 3‑D pose constraints?
Yes, it accepts pose constraints as a matrix of 3‑D joint positions and indices.
Is the model licensed for commercial use?
Yes, it is released under the NVIDIA Open Model License and is ready for commercial deployment.