Zythoz/gemma4-coding-agent

1---2tags:3- gguf4- llama.cpp5- unsloth6- vision-language-model7---8 9# gemma4-coding-agent : GGUF10 11This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).12 13**Example usage**:14- For text only LLMs:    `llama-cli -hf S4MPL3BI4S/gemma4-coding-agent --jinja`15- For multimodal models: `llama-mtmd-cli -hf S4MPL3BI4S/gemma4-coding-agent --jinja`16 17## Available Model files:18- `gemma-4-E4B-it.Q4_K_M.gguf`19- `gemma-4-E4B-it.BF16-mmproj.gguf`20 21## ⚠️ Ollama Note for Vision Models22**Important:** Ollama currently does not support separate mmproj files for vision models.23 24To create an Ollama model from this vision model:251. Place the `Modelfile` in the same directory as the finetuned bf16 merged model263. Run: `ollama create model_name -f ./Modelfile`27   (Replace `model_name` with your desired name)28 29This will create a unified bf16 model that Ollama can use.30This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)31[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)32