gemma_3_finetune_GGUF_Z32M : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf k-lauren/gemma_3_finetune_GGUF_Z32M --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf k-lauren/gemma_3_finetune_GGUF_Z32M --jinja

Available Model files:

• gemma-3-27b-it.Q8_0.gguf
• gemma-3-27b-it.BF16-mmproj.gguf
• gemma-3-27b-it.BF16-00002-of-00002.gguf

⚠️ Ollama Note for Vision Models

1. Place the Modelfile in the same directory as the finetuned bf16 merged model
2. Run: ollama create model_name -f ./Modelfile (Replace model_name with your desired name)

Note

The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth