gemma_SFT : GGUF

• For text only LLMs: llama-cli -hf Rufini/gemma_SFT --jinja
• For multimodal models: llama-mtmd-cli -hf Rufini/gemma_SFT --jinja

Available Model files:

• gemma-3-270m-it.Q8_0.gguf

Ollama

Note

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