fal makes MiniMax's open-source video model H3 35x faster, GPU utilization hits 70-80%
astrange · x · 2026-09-18
fal engineers rebuilt MiniMax's open-source H3 video model: fewer steps and rewritten stage code pushed GPU utilization from 30-40% to 70-80% of theoretical ceiling with no quality loss — 35x faster, generating video faster than you can film it.
Key points:
- Director mode and voice prompting let users move the camera and guide action live
- Speed and cost are no longer the pain point; quality and prompt-following are the new frontier
- Hollywood, absent a year ago, is now seriously engaging with generative video
Related event: fal Speeds Up MiniMax Open-Source Video Model 35x(4 posts)→
More from Infra
- Bonsai 2 27B ships with ternary weights: 5.95GB model hits 98.2% of FP16 benchmarks — airesearch12 · 2026-09-18
- Brad Gerstner at All-In Summit: who pays for AI CapEx, the gigawatt gap and semis eating the Nasdaq — DavidSacks · 2026-09-18
- Third-party audit reproduces Gensyn open-1b training step bit-for-bit — benfielding · 2026-09-18
- Anthropic Open-Sources Claude-Written GPU Optimizations Speeding 30+ Biomolecular Models ~4x — ResultBackground2450 · 2026-09-18
- Spotify: 777M users, 11-12M requests/sec — how AI changed its quality playbook — rseroter · 2026-09-18
- 605 new Linux kernel CVEs disclosed in one day, on top of 276 the day before — jedisct1 · 2026-09-18