gemma-4-12b-alex-q4-k-m-think : GGUF

• For text only LLMs: llama-cli -hf rodolpheb/gemma-4-12b-alex-q4-k-m-think --jinja
• For multimodal models: llama-mtmd-cli -hf rodolpheb/gemma-4-12b-alex-q4-k-m-think --jinja

Available Model files:

• gemma-4-12B-it.Q4_K_M.gguf
• gemma-4-12B-it.BF16-mmproj.gguf This was trained 2x faster with Unsloth