llama3.2-noinstructv1.6.3 : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf xensive/llama3.2-noinstructv1.6.3 --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf xensive/llama3.2-noinstructv1.6.3 --jinja

Available Model files:

• llama-3.2-3b.Q4_K_M.gguf

Note

The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth