ToPo-ToPo/Ornith-1.0-9B-mlx-bf16
MLX bf16 conversion of deepreinforce-ai/Ornith-1.0-9B for Apple Silicon (mlx-vlm).
Provenance (self-converted from official weights)
- Source:
deepreinforce-ai/Ornith-1.0-9B(license: mit) - Tool:
mlx-vlm 0.6.3—mlx_vlm.convert --hf-path deepreinforce-ai/Ornith-1.0-9B --mlx-path . --dtype bfloat16 - Effective: 16.0 bits/weight
- Validation: reproduced geometrically exact CAD output in an agentic CAD+FEM pipeline (volumes match the reference mlx-community conversion).
Usage
from mlx_vlm import load, generate
model, processor = load("ToPo-ToPo/Ornith-1.0-9B-mlx-bf16")