MachGen pushes MiniMax H3 past its 15s cap with 30-second continuous video
MiniMax_AI · x · 2026-10-02
MiniMax reshared third-party inference platform MachGen's announcement: MachGen now offers 16-30s continuous generation for MiniMax H3, breaking past the model's native 15-second cap — a single uninterrupted sequence, not stitched clips. Available now in open beta on UI and API. MachGen claims major speedups (up to 15x on H3) for open image/video models like MiniMax H3, LTX 2.3, HiDream O1 and Flux 2 Dev via an optimized inference platform.
More from Infra
- Investor: market hates uncertainty more than money after Nvidia earnings — MartinGTobias · 2026-11-19
- SGLang ships Day-0 serving support for new model DaisyRose-27B — ying11231 · 2026-11-19
- Linux LTS patch flood: 3318 patches for 6.6 alone, 'no way humans are reviewing this' — pkqzy888 · 2026-11-19
- DaisyRose-27B's in-house sandbox: ~80% cheaper than cloud providers, 99.95% success rate — BanghuaZ · 2026-11-19
- Tencent's 220B Hy4-flash quantized to 49 GB weights, runnable on 64 GB VRAM — gladkos · 2026-11-19
- Berth: a lightweight open-source GPU resource manager with multi-GPU scheduling and VRAM parking — Distinct-Pie2389 · 2026-11-19