Ezra-2B-LifeOS-v2 : GGUF

• For text only LLMs: llama-cli -hf CosmicBull/Ezra-2B-LifeOS-v2 --jinja
• For multimodal models: llama-mtmd-cli -hf CosmicBull/Ezra-2B-LifeOS-v2 --jinja

Available Model files:

• Qwen3.5-2B.Q8_0.gguf
• Qwen3.5-2B.BF16-mmproj.gguf This was trained 2x faster with Unsloth