Instructions to use DeepBeepMeep/3D with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use DeepBeepMeep/3D with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use DeepBeepMeep/3D with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf DeepBeepMeep/3D:Q4_K_M # Run inference directly in the terminal: llama cli -hf DeepBeepMeep/3D:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf DeepBeepMeep/3D:Q4_K_M # Run inference directly in the terminal: llama cli -hf DeepBeepMeep/3D:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf DeepBeepMeep/3D:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf DeepBeepMeep/3D:Q4_K_M
Use Docker
docker model run hf.co/DeepBeepMeep/3D:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use DeepBeepMeep/3D with Ollama:
ollama run hf.co/DeepBeepMeep/3D:Q4_K_M
- Unsloth Desktop
- Pi
How to use DeepBeepMeep/3D with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DeepBeepMeep/3D:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "DeepBeepMeep/3D:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use DeepBeepMeep/3D with Docker Model Runner:
docker model run hf.co/DeepBeepMeep/3D:Q4_K_M
- Lemonade
How to use DeepBeepMeep/3D with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull DeepBeepMeep/3D:Q4_K_M
Run and chat with the model
lemonade run user.3D-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use DeepBeepMeep/3D with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DeepBeepMeep/3D:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default DeepBeepMeep/3D:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use DeepBeepMeep/3D with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DeepBeepMeep/3D:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "DeepBeepMeep/3D:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download hi3d/NOTICE from DeepBeepMeep/3D: direct link, hf CLI and curl.
- Browser
- Download file 3.03 kB
-
https://huggingface.co/DeepBeepMeep/3D/resolve/main/hi3d/NOTICE
- Command line
-
hf download hf://DeepBeepMeep/3D/hi3d/NOTICE
-
curl -L -o NOTICE https://huggingface.co/DeepBeepMeep/3D/resolve/main/hi3d/NOTICE
3.03 kB
| SPARC3D | |
| Copyright 2026 The SPARC3D Authors | |
| This product includes software developed by third parties. The following | |
| components are redistributed under their own licenses, reproduced in full in | |
| THIRD_PARTY_LICENSES.md: | |
| * Microsoft TRELLIS (MIT License) | |
| Copyright (c) Microsoft Corporation. | |
| https://github.com/microsoft/TRELLIS | |
| * Pointcept / Point Transformer V3 (MIT License) | |
| Copyright (c) 2023 Pointcept | |
| https://github.com/Pointcept/Pointcept | |
| * O-CNN, ocnn-pytorch (MIT License) | |
| Copyright (c) 2022 Peng-Shuai Wang <wangps@hotmail.com> | |
| https://github.com/octree-nn/ocnn-pytorch | |
| * NVIDIA FlexiCubes (Apache License 2.0) | |
| Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES | |
| https://github.com/nv-tlabs/FlexiCubes | |
| License also included at sparc3d/ops/flexicubes/LICENSE.txt | |
| GPU surface voxelization in sparc3d/ops descends from the PyTorch extension | |
| written by Zhihao Li; see AUTHORS. | |
| Hi3D v1.0 | |
| --------- | |
| Hi3D v1.0 includes the SPARC3D inference implementation. Original copyright, | |
| attribution, license texts, and per-file modification notices are retained. | |
| The Python package and API names are sparc3d / Sparc3DPipeline. | |
| Hunyuan3D is referenced only by an optional coarse-mesh example adapter. Tencent's | |
| Hunyuan3D implementation and weights are not bundled with or relicensed by this | |
| distribution. External image encoders and any separately obtained model weights | |
| retain their own terms. See THIRD_PARTY_LICENSES.md for the source and model | |
| license index. | |
| Hi3D Open License Agreement Version 1.0 notice | |
| -------------------------------------------- | |
| The following notice applies to the Hi3D Materials identified in Schedule 2 of | |
| LICENSE, only to the extent OCEANO HK HOLDING LIMITED owns or is authorized to | |
| license them. It does not replace the original third-party notices above or | |
| extend the Agreement to Excluded Materials. See THIRD_PARTY_LICENSES.md. | |
| Hi3D is licensed under the Hi3D Open License Agreement Version 1.0. Copyright © 2026 OCEANO HK HOLDING LIMITED. All rights not expressly granted are reserved. The Hi3D trademarks are owned by OCEANO HK HOLDING LIMITED or its applicable affiliate(s). | |
| Modified files (DeepBeepMeep, WanGP, 2026-10-28) | |
| ---------------------------------------------- | |
| The Hi3D v1.0 weights were repackaged for WanGP; no weight was retrained: | |
| * hi3d_transformer_512_bf16.safetensors, hi3d_transformer_1024_bf16.safetensors: | |
| the 512 and 1024 transformers with every floating-point tensor stored in BF16 | |
| (upstream: FP16 torso, FP32 modulations and norms). | |
| * hi3d_transformer_512_int8_convrot.safetensors, hi3d_transformer_1024_int8_convrot.safetensors: | |
| the same transformers with their linear weights quantized to INT8 (ConvRot). | |
| * hi3d/hi3d_vae_fp16.safetensors: the decoder stored in FP16 (upstream FP32), | |
| without its constant inv_grid_coord tables (a constant in WanGP's code). | |
| * hi3d/clip_vit_large_patch14_vision_fp16.safetensors: the vision tower of | |
| openai/clip-vit-large-patch14 (MIT) in FP16; not a Hi3D material. | |