gemma-3-1b-it-finetune-Q8 : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf WildOjisan/gemma-3-1b-it-finetune-Q8 --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf WildOjisan/gemma-3-1b-it-finetune-Q8 --jinja

Available Model files:

• gemma-3-1b-it.Q8_0.gguf

Ollama

Note

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