Llama-3.2-1B-Instruct-GGUF : GGUF

• For text only LLMs: llama-cli -hf Xlr8boi/Llama-3.2-1B-Instruct-GGUF --jinja
• For multimodal models: llama-mtmd-cli -hf Xlr8boi/Llama-3.2-1B-Instruct-GGUF --jinja

Available Model files:

• Llama-3.2-1B.Q5_K_M.gguf
• Llama-3.2-1B.F16.gguf
• Llama-3.2-1B.Q8_0.gguf
• Llama-3.2-1B.Q4_K_M.gguf This was trained 2x faster with Unsloth