# Native MLX H3 server. Run from the repository root after downloading and converting weights.
runtime: mlx
generator:
  model_path: FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2
  model_root: ./FastH3-Preview-v0.2
  mlx_checkpoint: ./FastH3-MLX/int6
  prompt_cache_dir: ./outputs/h3_prompt_cache
  vae_dtype: fp32
server:
  host: 127.0.0.1
  port: 8000
  served_model_name: fasth3
  output_dir: outputs/mlx_fasth3
default_request:
  sampling:
    height: 480
    width: 832
    num_frames: 124
    fps: 24
    # HTTP convention: five sigma points, four DiT forwards. Native MLX uses num_steps=4.
    num_inference_steps: 5
    guidance_scale: 1.0
    seed: 2026