Ezra-4B-LifeOS : GGUF

• For text only LLMs: llama-cli -hf CosmicBull/Ezra-4B-LifeOS --jinja
• For multimodal models: llama-mtmd-cli -hf CosmicBull/Ezra-4B-LifeOS --jinja

Available Model files:

• Qwen3.5-4B.Q6_K.gguf
• Qwen3.5-4B.BF16-mmproj.gguf This was trained 2x faster with Unsloth