PulseAugur
EN
LIVE 00:41:16

MiniMax H3 video generation achieves 2x speedup on Nvidia B200

By PulseAugur Editorial · [1 sources] ·

MiniMax AI has announced significant speed improvements for its H3 video generation model. Utilizing SGLang-Diffusion and VDN-H3 on eight Nvidia B200 GPUs, the system can now generate 14.4 seconds of 768p video in just 9.0 seconds. This represents a speed increase of over two times real-time denoising without any observable loss in video quality. AI

IMPACT Demonstrates continued progress in efficient video generation, potentially lowering barriers for real-time AI video applications.

RANK_REASON Research milestone announcement regarding model performance improvements. [lever_c_demoted from research: ic=1 ai=1.0]

Read on X — MiniMax AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

MiniMax H3 video generation achieves 2x speedup on Nvidia B200

How we ranked this

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research milestone announcement regarding model performance improvements. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. X — MiniMax AI TIER_1 Dansk(DA) · MiniMax_AI ·

    H3 keeps getting faster. ⚡️

    H3 keeps getting faster. ⚡️ @sgl_project + VDN-H3 now push MiniMax H3 beyond 2× real-time denoising on 8× B200 - generating 14.4s of 768p video in 9.0s end-to-end after warmup, with no measured quality regression. Open models compound through open ecosystems. 🚀

RELATED ENTITIES

RELATED TOPICS