gemma3-12b-vinglish : GGUF

• For text only LLMs: llama-cli -hf datmt/gemma3-12b-vinglish --jinja
• For multimodal models: llama-mtmd-cli -hf datmt/gemma3-12b-vinglish --jinja

Available Model files:

• gemma-3-12b-it.BF16.gguf
• gemma-3-12b-it.BF16-mmproj.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