lexsumm-llama3.2-3b-gguf : GGUF

• For text only LLMs: llama-cli -hf Tripti0911/lexsumm-llama3.2-3b-gguf --jinja
• For multimodal models: llama-mtmd-cli -hf Tripti0911/lexsumm-llama3.2-3b-gguf --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