MiniMax H3 Gets Day 0 Support in SGLang, Runs Locally on Dual RTX 5090s
ying11231 · x · 2026-08-03
The MiniMax H3 model now has Day 0 support in @lmsysorg and is live in SGLang Diffusion. Developers can run the model locally and for free on their own machines using 2x RTX 5090 or 1 RTX 6000 GPU, incurring no API costs.
The model processes text, image, video, and audio inputs to generate 5-15 second clips at native 2K resolution, 24fps with native stereo audio. The underlying stack is compatible with NVIDIA Blackwell/Hopper architectures as well as AMD MI355X/MI300X hardware.
Related event: MiniMax Video Model Goes Viral with Stunning User Tests(61 posts)→
More from Infra
- Meta's commitments jumped to $349B in a quarter as server memory prices tripled ahead of Oct 21 earnings — tengyanAI · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- CoreWeave plunges 20% as credit markets price >60% default odds; is this dot-com all over again? — kimmonismus · 2026-10-16
- MiniCPM-V 4.7 35B-A3B hits 17+ tokens/s on iPad with ~3GB memory — techNmak · 2026-10-16
- China rolls out 'token factories' and a 2026-28 token economy action plan — nordicinst · 2026-10-16