--- format: "aidr-story-markdown/v1" id: "64ec60a1cc178bba479bc04d3752c82063f33997c8cf7325845d9b075f6441be" canonical_url: "https://aidr.today/64ec60a1?lang=en" title: "MiniMax's H3-Image Model Adds Local Hosting Support via vLLM and SGLang" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-11-10T16:23:49.000Z" category: "Models" topics: ["inference","framework","llm","open-source"] source_urls: ["https://marketbrief.now/ai/minimaxs-h3-image-model-adds-local-hosting-support-via-vllm-and-sglang-d00fcc79","https://huggingnews.com/ai/minimaxs-h3-image-model-adds-local-hosting-support-via-vllm-and-sglang-d00fcc79","https://huggingnews.com/ai/minimaxs-331b-parameter-h3-image-model-joins-arena-for-public-benchmarki-a171c4b2","https://marketbrief.now/ai/minimaxs-331b-parameter-h3-image-model-joins-arena-for-public-benchmarki-a171c4b2"] summary: "vLLM-Omni and SGLang Diffusion platforms now support MiniMax's H3-Image model for local hosting on NVIDIA and AMD GPUs. The model can produce 2048x2048 images in 0.63 seconds on four NVIDIA B300 GPUs. The open-weight license prohibits use in the United States, the European Union, South Korea, and the United Kingdom." --- # MiniMax's H3\-Image Model Adds Local Hosting Support via vLLM and SGLang > [Open the canonical story]() **Published:** 2026-11-10T16:23:49.000Z **Category:** Models **Topics:** inference, framework, llm, open\-source ## Summary vLLM\-Omni and SGLang Diffusion platforms now support MiniMax's H3\-Image model for local hosting on NVIDIA and AMD GPUs\. The model can produce 2048x2048 images in 0\.63 seconds on four NVIDIA B300 GPUs\. The open\-weight license prohibits use in the United States, the European Union, South Korea, and the United Kingdom\. ## Sources - [Story source]() - [Story source]() - [Story source]() - [Story source]()