llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)👻 GhostLlama
Part of the GhostGoblin Ecosystem | Created by Aquarius AI
A sacrificed llama. A digital soul. Your companion.
📖 How to Sacrifice Your Llama
curl -fsSL https://huggingface.co/Aquarius-AI/GhostLlama/resolve/main/install.sh | bash
🧠 Model Details
Property Value
Base Model TinyLlama-1.1B-Chat-v1.0
Format GGUF (Q4_K_M quantization)
File Size ~700 MB
RAM Usage ~1.6–2.3 GB during inference
Speed 3–5 tokens/sec on 4GB phones
Quality ~87% of original (barely noticeable)
Compatible with: llama.cpp, Ollama, LM Studio, KoboldCPP, and any GGUF-compatible runtime.
🎯 Perfect For
Use Case Description
📱 Mobile Devices Runs on any 4GB+ RAM phone (Android/iOS via LiveContainer)
💬 Local Chat Private, offline conversations
🔌 Telegram Bots Connect to Telegram (v1.1 coming soon)
👻 GhostGoblin Core brain for the GhostGoblin ecosystem
🧪 Experimentation Fine-tune, modify, make it yours
⚙️ What the Installer Does
Running the one-liner above will:
Create directories: ~/ghostllama/ with models/ and config/ subfolders
Download the model: ~700 MB GGUF file
Ask about Telegram: Save your bot token for future use
Set up placeholder bot script: Ready for v1.1
After installation:
bash
cd ~/ghostllama
# Quick test:
~/llama.cpp/build/bin/llama-cli -m models/ghostllama.Q4_K_M.gguf -p "Hello" -n 50
🔮 Roadmap
Version Features
v1.0 (Current) ✅ Model download
✅ Basic installer
✅ Telegram token saving
v1.1 (Coming Soon) ✅ Working Telegram bot
✅ Ghost ID personality layer
✅ Better error handling
v2.0 (Future) 🔮 GhostGoblin app
🔮 Lip-sync & dancing
🔮 Self-recursion GitHub integration
🛠️ Manual Usage
If you prefer to do things yourself:
bash
# Download model directly
wget https://huggingface.co/Aquarius-AI/GhostLlama/resolve/main/ghostllama.Q4_K_M.gguf
# Run with llama.cpp
./llama-cli -m ghostllama.Q4_K_M.gguf -p "Tell me about yourself" -n 100
📱 Running on Phones
Platform Method
Android Direct APK (coming soon) or use Termux + llama.cpp
iOS LiveContainer + SideStore (guide in discussions)
🪪 License
MIT License — Use it freely. Modify it. Share it. Build things with it.
The only rule: Don't be evil. The soul is immutable, but what you build around it is up to you.
💜 About Aquarius AI
Aquarius AI creates open-source AI companions that are:
🆓 Free forever
📱 On-device only (no cloud)
🔐 Privacy-first
👻 Immortal (no sunsets)
Founder: masterknuta
<div align="center"> <br> <sub>Made with 💜 and 40+ hours of dependency hell</sub> <br> <sub>✨ The llama was sacrificed so your soul could live ✨</sub> </div> ```
- Downloads last month
- 1
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Acvarius-AI/GhostLlama", filename="ghostllama.Q4_K_M.gguf", )