Text Generation
GGUF
English
blender
3d
tool-calling
llama.cpp
ollama
lora
small-language-model
slm
offline
uncensored
Eval Results (legacy)
conversational
Instructions to use slm4apps/Maris3D-Blender with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use slm4apps/Maris3D-Blender 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 slm4apps/Maris3D-Blender:Q8_0 # Run inference directly in the terminal: llama cli -hf slm4apps/Maris3D-Blender:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf slm4apps/Maris3D-Blender:Q8_0 # Run inference directly in the terminal: llama cli -hf slm4apps/Maris3D-Blender:Q8_0
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 slm4apps/Maris3D-Blender:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf slm4apps/Maris3D-Blender:Q8_0
Use Docker
docker model run hf.co/slm4apps/Maris3D-Blender:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use slm4apps/Maris3D-Blender with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "slm4apps/Maris3D-Blender" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "slm4apps/Maris3D-Blender", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/slm4apps/Maris3D-Blender:Q8_0
- Ollama
How to use slm4apps/Maris3D-Blender with Ollama:
ollama run hf.co/slm4apps/Maris3D-Blender:Q8_0
- Unsloth Desktop
- Pi
How to use slm4apps/Maris3D-Blender with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf slm4apps/Maris3D-Blender:Q8_0
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": "slm4apps/Maris3D-Blender:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use slm4apps/Maris3D-Blender with Docker Model Runner:
docker model run hf.co/slm4apps/Maris3D-Blender:Q8_0
- Lemonade
How to use slm4apps/Maris3D-Blender with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull slm4apps/Maris3D-Blender:Q8_0
Run and chat with the model
lemonade run user.Maris3D-Blender-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use slm4apps/Maris3D-Blender with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf slm4apps/Maris3D-Blender:Q8_0
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 slm4apps/Maris3D-Blender:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use slm4apps/Maris3D-Blender with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf slm4apps/Maris3D-Blender:Q8_0
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 "slm4apps/Maris3D-Blender:Q8_0" \ --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 Modelfile from slm4apps/Maris3D-Blender: direct link, hf CLI and curl.
- Browser
- Download file 989 Bytes
-
https://huggingface.co/slm4apps/Maris3D-Blender/resolve/main/Modelfile
- Command line
-
hf download hf://slm4apps/Maris3D-Blender/Modelfile
-
curl -L -o Modelfile https://huggingface.co/slm4apps/Maris3D-Blender/resolve/main/Modelfile
989 Bytes
| # Maris3D SLM Blender 0.5B 0.2.1 -- Ollama entry "maris3d-slm-blender-0.5b" (tags :latest and :0.2.1): the base with the 0.2 adapter (plans, parts, word edits, talk). | |
| # ollama create maris3d-slm-blender-0.5b -f Modelfile | |
| # ollama cp maris3d-slm-blender-0.5b maris3d-slm-blender-0.5b:0.2.1 # the same model under its version tag | |
| # The Maris3D app sends these same settings on every request (src/maris3d/runtimes/ollama.py); they are here | |
| # so a direct call matches. Ollama's own default repeat_penalty (1.1) is not what the adapter was measured with. | |
| FROM ./maris3d-slm-blender-0.5b-q8_0.gguf | |
| ADAPTER ./maris3d-slm-blender-0.5b-v0.2.1-lora-f16.gguf | |
| PARAMETER temperature 0 | |
| PARAMETER repeat_penalty 1.05 | |
| PARAMETER num_ctx 8192 | |
| PARAMETER num_predict 1024 | |
| # Default system line, used only when a request has no system message (the app always sends its own). | |
| SYSTEM """You are Maris, the Maris3D model by slm4apps. You build and change 3D scenes in Blender from plain words, offline.""" | |