Llama-3.2-3B-bnb-4bit-3 : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf yhily/Llama-3.2-3B-bnb-4bit-3 --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf yhily/Llama-3.2-3B-bnb-4bit-3 --jinja

Available Model files:

• llama-3.2-3b-instruct.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment. This was trained 2x faster with Unsloth