LingBot-World-V2 1.3B causal-fast
M4 Pro 48GB · PyTorch MPS
- quant:
- 8-bit (MLX)
video-generation
User ports LingBot-World-V2 1.3B causal-fast video world model to a single M4 Pro 48GB Mac via PyTorch MPS, generating 109 frames of 480x832 video (6.8 seconds at 16 fps) in 14.4 minutes with a 16.1 GB peak footprint. Setup uses an MLX 8-bit umt5-xxl text encoder (5.6 GB on disk, ~1 s per prompt) and a spatially tiled VAE decode; the text encoder, DiT and VAE are never resident simultaneously. Peak footprint stays at ~16 GB whether generating 121 or 361 frames. User notes the port is not real-time, only tested on one machine, and that 4-bit text encoder quantization was rejected due to 17-28% relative error. A torch bf16 run of 361 frames took 33.5 minutes.