PulseAugur
EN
LIVE 06:29:17

MiniMax AI releases open-source H3 multimodal model with vLLM and SGLang support

By PulseAugur Editorial · [2 sources] ·

MiniMax AI has released the open weights for its H3 model, which supports multimodal inputs including text, images, and video, and can generate video with audio. The model is now available with day-0 support on platforms like vLLM-Omni and lmsysorg's SGLang Diffusion. This release aims to make the model easier to serve and build upon, running on NVIDIA and AMD hardware, and is positioned as a competitive option in the rapidly evolving open-source model landscape. AI

IMPACT Accelerates open-source multimodal model development and deployment, offering a competitive alternative for video generation tasks.

RANK_REASON Open weights release of a multimodal model from a frontier lab (MiniMax AI). [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on X — MiniMax AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

MiniMax AI releases open-source H3 multimodal model with vLLM and SGLang support

COVERAGE [2]

  1. X — MiniMax AI TIER_1 English(EN) · MiniMax_AI ·

    Open weights are step one. Making them easy to serve is step two. H3 now has Day 0 support in @vllm_project's vLLM-Omni, complete with an OpenAI-compatible vide

    Open weights are step one. Making them easy to serve is step two. H3 now has Day 0 support in @vllm_project's vLLM-Omni, complete with an OpenAI-compatible video endpoint. Huge thanks to the vLLM team for bringing H3 into the open inference stack. ⚡ #MiniMaxH3 #OpenWeights

  2. X — MiniMax AI TIER_1 English(EN) · MiniMax_AI ·

    H3 now has Day 0 support in @lmsysorg -- local, customizable, and ready to build on across @NVIDIAAI and @AMD hardware.

    H3 now has Day 0 support in @lmsysorg -- local, customizable, and ready to build on across @NVIDIAAI and @AMD hardware. #MiniMaxH3 #OpenWeights

RELATED ENTITIES

RELATED TOPICS