llama-3.2-B-Instruct-bnb-4bit-demo : GGUF

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