MiniMax H3 runs 720p to 1440p on one RTX 4090 with sparse attention
An independent developer built an auto-scheduled sparse-attention system for X-MinimaxH3, enabling native second sampling from 720p to 1440p on a single RTX 4090. Measured times: 112s, 223s, and 334s for the three resolutions.
1 source
AI Models by email
Get an email when there's news on AI Models
No news that day, no email.
More stories today
- Empirik launches with $21M to predict IT outages
- Musk: AI to boost global economy 20-30%
- Atos upskills 400 engineers in agentic AI with AWS
- Top AI open source projects shut off PRs, use own agents
- AWS details securing Amazon Quick from POC to production