gemma3.4bft : GGUF

• For text only LLMs: llama-cli -hf rizqiv2/gemma3.4bft --jinja
• For multimodal models: llama-mtmd-cli -hf rizqiv2/gemma3.4bft --jinja

Available Model files:

• gemma-3-4b-it.Q4_K_M.gguf
• gemma-3-4b-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