Llama-3-TFG-Robotica-8B-GGUF-v4 : GGUF

• For text only LLMs: llama-cli -hf Joaquinocho999/Llama-3-TFG-Robotica-8B-GGUF-v4 --jinja
• For multimodal models: llama-mtmd-cli -hf Joaquinocho999/Llama-3-TFG-Robotica-8B-GGUF-v4 --jinja

Available Model files:

• llama-3.2-3b-instruct.Q4_K_M.gguf

Ollama

Note

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