Ornith 1.0 35B FP8 is a text-in, text-out open-weight model from deepreinforce-ai, quantized to FP8 precision — a format that trades a small amount of numerical fidelity for reduced memory footprint and faster inference. At 35 billion parameters, it sits in a mid-to-large weight class. Specific capability details are limited, so concrete behavioral traits aren't well documented.