Instructions to use moolvylabs/Morphy-360M-GGUF 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 moolvylabs/Morphy-360M-GGUF 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 moolvylabs/Morphy-360M-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf moolvylabs/Morphy-360M-GGUF:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf moolvylabs/Morphy-360M-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf moolvylabs/Morphy-360M-GGUF:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf moolvylabs/Morphy-360M-GGUF:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf moolvylabs/Morphy-360M-GGUF:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf moolvylabs/Morphy-360M-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf moolvylabs/Morphy-360M-GGUF:Q8_0
Use Docker
docker model run hf.co/moolvylabs/Morphy-360M-GGUF:Q8_0
- LM Studio
- Jan
- vLLM
How to use moolvylabs/Morphy-360M-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "moolvylabs/Morphy-360M-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moolvylabs/Morphy-360M-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/moolvylabs/Morphy-360M-GGUF:Q8_0
- Ollama
How to use moolvylabs/Morphy-360M-GGUF with Ollama:
ollama run hf.co/moolvylabs/Morphy-360M-GGUF:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use moolvylabs/Morphy-360M-GGUF with Docker Model Runner:
docker model run hf.co/moolvylabs/Morphy-360M-GGUF:Q8_0
- Lemonade
How to use moolvylabs/Morphy-360M-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull moolvylabs/Morphy-360M-GGUF:Q8_0
Run and chat with the model
lemonade run user.Morphy-360M-GGUF-Q8_0
List all available models
lemonade list
- Atomic Chat
Morphy-360M is the second model in the Morphy lineup (or family) developed by the Moolvylabs team. The model was trained entirely on our proprietary datasets and is optimized for ultra-fast, lightweight performance on local machines.
โจ Strengths (What the model excels at)
- โ๏ธ Business Correspondence โ the model is highly capable of writing, editing, and structuring professional emails, cold outreach, and corporate announcements.
- ๐ Text Editing & Copywriting โ it excels at correcting grammatical errors, adjusting text tone, and composing high-quality documentation.
- ๐ข Brand Integration โ natively understands and integrates company context (like Moolvylabs) into professional communications.
โ ๏ธ Important Features and Limitations
Since this is a super-compact model with 360M parameters, it is important for users to keep the following nuances in mind:
- ๐ฌ Complex and Scientific Topics: The model is prone to making mistakes in highly complex topics, as well as academic queries related to advanced physics or biology.
- ๐ Context Management: For long multi-turn dialogues, it is highly recommended to periodically clear the context (
/clear) to maintain maximum accuracy and prevent repetitive loops.
๐ ๏ธ Technical Specifications
| Parameter | Value |
|---|---|
| Name | Morphy-360M |
| Generation | Second model in the family |
| Base Model | SmolLM2-360M |
| Data Type | Custom Moolvylabs Datasets |
| Purpose | Email Generation / Text Editing & Copywriting |
- Downloads last month
- 30
Hardware compatibility
Log In to add your hardware
8-bit