Pythonified-Llama-3.2-3B-Instruct-GGUF

Pythonified-Llama-3.2-3B-Instruct - GGUF Quantized

Quantized GGUF versions of Pythonified-Llama-3.2-3B-Instruct for use with llama.cpp and other GGUF-compatible inference engines.

Original Model

• Base model: meta-llama/Llama-3.2-3B-Instruct
• Fine-tuned model: theprint/Pythonified-Llama-3.2-3B-Instruct
• Quantized by: theprint

Available Quantizations

• Pythonified-Llama-3.2-3B-Instruct-f16.gguf (6135.6 MB) - 16-bit float (original precision, largest file)
• Pythonified-Llama-3.2-3B-Instruct-q3_k_m.gguf (1609.0 MB) - 3-bit quantization (medium quality)
• Pythonified-Llama-3.2-3B-Instruct-q4_k_m.gguf (1925.8 MB) - 4-bit quantization (medium, recommended for most use cases)
• Pythonified-Llama-3.2-3B-Instruct-q5_k_m.gguf (2214.6 MB) - 5-bit quantization (medium, good quality)
• Pythonified-Llama-3.2-3B-Instruct-q6_k.gguf (2521.4 MB) - 6-bit quantization (high quality)
• Pythonified-Llama-3.2-3B-Instruct-q8_0.gguf (3263.4 MB) - 8-bit quantization (very high quality)

Usage

With llama.cpp

# Download recommended quantization
wget https://huggingface.co/theprint/Pythonified-Llama-3.2-3B-Instruct-GGUF/resolve/main/Pythonified-Llama-3.2-3B-Instruct-q4_k_m.gguf

# Run inference
./llama.cpp/main -m Pythonified-Llama-3.2-3B-Instruct-q4_k_m.gguf \
  -p "Your prompt here" \
  -n 256 \
  --temp 0.7 \
  --top-p 0.9

With other GGUF tools

These files are compatible with:

• llama.cpp
• Ollama (import as custom model)
• KoboldCpp
• text-generation-webui

Quantization Info

Recommended: q4_k_m provides the best balance of size, speed, and quality for most use cases.

For maximum quality: Use q8_0 or f16
For maximum speed/smallest size: Use q3_k_m or q4_k_s

License

apache-2.0

Citation

@misc{pythonified_llama_3.2_3b_instruct_gguf,
  title={Pythonified-Llama-3.2-3B-Instruct GGUF Quantized Models},
  author={theprint},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/theprint/Pythonified-Llama-3.2-3B-Instruct-GGUF}
}