vLLM-Omni adds day-0 support for MiniMax H3-Image on NVIDIA Vera Rubin
Overview
vLLM-Omni says it brought MiniMax H3-Image to NVIDIA Vera Rubin GPUs on launch day, according to a first-party vLLM Blog post dated 2026-11-11.
In a short-prompt serving benchmark on four GPUs, the post reports a 0.87-second median generation time for 4K images. A separate throughput configuration with four single-GPU replicas reaches 6,115 images per hour.
The post also projects revenue of USD 78.87 to 105.16 per GPU per hour, before operating costs. It assumes a sale price based on MiniMax's Standard 4K API price. These figures come from vLLM-Omni's own benchmark and projection, and no independent measurement is reported.
Written by AI from the articles below · updated Nov 12, 3:42 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- vLLM BlogOfficialvLLM-Omni adds day-0 support for MiniMax H3-Image on Vera Rubin GPUs
AIvLLM-Omni says it brought MiniMax H3-Image to NVIDIA Vera Rubin, with 0.87-second median 4K generation on four GPUs in a short-prompt serving benchmark. A separate throughput configuration reaches 6,115 images per hour with four single-GPU replicas. The post also projects revenue of USD 78.87 to 105.16 per GPU per hour, before operating costs, using MiniMax's Standard 4K API price as an assumed sale price.
Heat Trend
- Current comparable heat
- 7
- Peak comparable heat
- 8Nov 12, 4:00 AM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.