How to use from
Pi
Start the llama.cpp server
# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf scriptedvn/scriptedvn-models: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": "scriptedvn/scriptedvn-models:Q4_K_M"
        }
      ]
    }
  }
}
Run Pi
# Start Pi in your project directory:
pi
Quick Links

ScriptedVN model files

Open models redistributed for the ScriptedVN desktop app (Ren'Py visual novel translation). Files are unmodified or format-converted; each folder keeps the original license.

Folder Model Original License
madlad400_3b/ MADLAD-400 3B, converted to CTranslate2 int8 google/madlad400-3b-mt Apache-2.0
hymt_1_8b/ Hy-MT2 1.8B, GGUF Q4_K_M tencent/Hy-MT2-1.8B Apache-2.0
qwen_3_5_4b_gguf/ Qwen3.5-4B, GGUF Q4_K_M + mmproj Qwen Apache-2.0

The app downloads these files at a fixed revision and verifies each file's SHA-256.

Downloads last month
184
GGUF
Model size
4B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support