Onyx-FastWan22-TI2V-5B-mlx-4bit

• Transformer: 5B dense DiT, 4-bit affine (group 64), norms/embeddings high-precision — 2.6 GB
• Text encoder: umT5-XXL, 4-bit affine (group 64) — 3.0 GB
• VAE: Wan 2.2 3D causal VAE, float32 (decode precision is load-bearing) — 2.6 GB
• Inference: 3 steps, no CFG, DMD timesteps [1000, 757, 522] (σ = t/1000 — the list is already in post-shift space; do not re-apply flow_shift)
• Modes: text-to-video and image-to-video (TI2V: conditioning image pinned over latent frame 0, its tokens at timestep 0)
• Native grid: 121 frames × 704 × 1280 @ 24 fps (other resolutions run, quality degrades away from the trained grid)

Attribution & license