ravikadam/illuminezilladraft-qwen3-4b-gguf

Illumine Zilla Draft — Qwen3 4B (GGUF)

This repo contains:

• a GGUF model file
• an Ollama Modelfile (template + stop tokens + generation params) to prevent repetition

Quick run (run GGUF directly from Hugging Face)

ollama run hf.co/ravikadam/illuminezilladraft-qwen3-4b-gguf

Note: Running the GGUF directly may not apply the custom template/stop parameters from the Modelfile.

Best chat behavior (recommended): create with Modelfile

git clone https://huggingface.co/ravikadam/illuminezilladraft-qwen3-4b-gguf
cd illuminezilladraft-qwen3-4b-gguf

ollama create zilla:fp16 -f Modelfile
ollama run zilla:fp16

Files

• qwen3-4b-zilla-fp16.gguf — model weights (Git LFS)
• Modelfile — Ollama template + generation parameters