llama-3-8b-Instruct-bnb-4bit-aiaustin-demo : GGUF

• For text only LLMs: llama-cli -hf llama-3-8b-Instruct-bnb-4bit-aiaustin-demo --jinja
• For multimodal models: llama-mtmd-cli -hf llama-3-8b-Instruct-bnb-4bit-aiaustin-demo --jinja

Available Model files:

• llama-3-8b-instruct.Q4_K_M.gguf

Ollama

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