The story’s score and claims

Comments on No. 10 of 51 · GitHub · edition of Sunday 8 November 2026

We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

Summary

Video Rebirth released HyperFlow H3 Flash, a pruned, INT8-quantized, few-step version of MiniMax-H3 that generates video with synchronized stereo audio. It has 13.7B–13.9B parameters versus about 31B, samples in 4–8 steps without classifier-free guidance, and ships GGUF builds (Q4_K_M is 9.1 GB) for 24 GB and 32 GB consumer GPUs. Its own timings are 8.7 s for a 5.2 s clip on 4× B200 and 92 s on one RTX 5090; these and the real-time claim are unverified. Weights exclude US, EU, UK and Korean use without MiniMax's authorization.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules