What’s the vram usage? I’ve got a 5090 so as long as I can fit it in memory the gen times should be roughly equivalent ~10%

Depends on what weights, I landed on:

    diffusion model: minimax_h3_fl2va_bf16.safetensors
    text encoder: qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
    video VAE: minimax_h3_video_vae_fp16.safetensors
    audio VAE: minimax_h3_audio_vae_fp32.safetensors