MiniMax H3 Gets Day-One SGLang Diffusion Support for Local 2K Video Generation
MiniMax H3 is now supported in SGLang Diffusion from launch day, enabling local deployment of an open-weights video model with multimodal inputs, native stereo audio, and output up to 2K at 24 fps.
MiniMax and LMSYS say H3 has received day-one serving support in SGLang Diffusion. The integration is intended for local and customizable workflows spanning video concepts, motion design, e-commerce creatives, animation, and precise video editing. Reported hardware coverage includes NVIDIA Blackwell and Hopper systems, along with selected AMD platforms.
H3 accepts text, images, video, and audio in a shared context and can generate clips of up to 15 seconds with native stereo sound. ComfyUI separately reported same-day support and described the model as an open-weights release designed for local inference.
Claims that H3 matches Seedance 2.0 at one-third the cost, or can run for no API charge on specific consumer GPUs, remain promotional and are not independently benchmarked in the supplied evidence. One AMD reference is also materially mismatched: it documents MiniMax M3 rather than H3, so it should not be treated as proof of H3 support on AMD Instinct hardware.
Source evidence
MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Videoblog.comfy.org · supportingComfyUI Newsletter # ComfyUI Newsletter # MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video ### An open-weights omni-modal video model with real stereo sound and 2K output — this powerful model is greatly optimized in ComfyUI and can run locally on a 3060. Rob's avatar Alexis Rolland's avatar MiniMax H3 dropped today with open weights, and it’s natively supported in ComfyUI as of this morning. Day zero. This is a next-generation open-weights video model. Feed it text, images, video, or audio and it generates video with real stereo sound, up to 2K, up to 15 seconds a clip. It is MiniMax’s third-generation video model, following Hailuo 01 and Hailuo 02, and the first the company has released with open weights. ## Model Highlights [...] ## Optimized for local inference in ComfyUI Getting H3 to run well on consumer hardware took significant machine learning engineering. We found that the model's modulation weights (~40% of the total parameters) could be
MiniMax H3 Open Weights Land With Native ComfyUI Supportcomfyui-wiki.com · supporting| Component | Files | --- | | Diffusion model | `minimax_h3_fl2va_bf16` (61.7 GB), `minimax_h3_fl2va_int8_convrot` (31.7 GB), `minimax_h3_fl2va_pruned_int8_convrot` (19.5 GB), plus matching `ref2va_` variants | | Text encoder | `qwen3vl_32b_minimax_h3_bf16` (48.0 GB), `int8_convrot` (25.3 GB), `nvfp4_awq` (14.6 GB) | | VAEs | `minimax_h3_video_vae_fp16` (4.9 GB), `minimax_h3_audio_vae_fp32` (0.6 GB) | The pruned INT8 checkpoints are about 40% smaller than the standard INT8 files thanks to precomputed adaLN curve tables, and the NVFP4 AWQ text encoder runs on any GPU. H3-Base deploys through SGLang, vLLM, diffusers, and ComfyUI. ## Native ComfyUI support merged [...] Ref2VA accepts up to 9 reference images, 3 reference videos (2-15 s each, 15 s total max), and 3 reference audio clips (2-15 s each, 15 s total max, always alongside an image or video). Mixed input is capped at 12 files total. ## Open weights on Hugging Face Two repositories are now live: MiniMaxAI/MiniMax-H3 (Huggin
MiniMax H3 Gains Day-0 Support in SGLang Diffusion · Diggdigg.com · supporting5090 ordered, SGLang installed, H3 downloaded. 🤩 @MiniMax\_AI H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives,… Show more H3 now has Day 0 support in @lmsysorg -- local, customizable, and ready to build on across @NVIDIAAI and @AMD hardware. #MiniMaxH3 #OpenWeights @MiniMax\_AI H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives,… Show more [...] ## Sentiment ### Positive Read Many users praised MiniMax H3's day-0 SGLang support for enabling local customizable video generation with open weights and lower cost than Seedance, while a few raised concerns about matching p
SGLang is a high-performance serving framework for large ...github.com · supporting## News [2026/06] 🔥 The next generation of speculative decoding: DFlash and Spec V2 (blog). [2026/04] 🔥 DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles (blog). [2026/06] SGLang provides day-0 support for latest open models (Nemotron 3 Ultra, Nemotron 3 Super, Higgs Audio v3 TTS). [2026/02] 🔥 Unlocking 25x Inference Performance with SGLang on NVIDIA GB300 NVL72 (blog). [2026/01] SGLang Diffusion accelerates video and image generation (blog). [2025/12] SGLang provides day-0 support for latest open models (MiMo-V2-Flash, Nemotron 3 Nano, Mistral Large 3, LLaDA 2.0 Diffusion LLM, MiniMax M2). [2025/10] SGLang now runs natively on TPU with the SGLang-Jax backend (blog). More [...] [2025/01] SGLang provides day one support for DeepSeek V3/R1 models on NVIDIA and AMD GPUs with DeepSeek-specific optimizations. (instructions, AMD blog, 10+ other companies) [2024/12] v0.4 Release: Zero-Overhead Batch Scheduler, Cache-Aware Load Balancer, Faster Struct
Day 0 Support for MiniMax M3 on AMD Instinct GPUsamd.com · supporting## Deploying with SGLang By leveraging SGLang with ROCm support, developers can unlock high-throughput serving in ROCm. Support is available in the lmsysorg build of SGLang via docker image using the SGLang MiniMax M3 recipe. `lmsysorg/sglang:-rocm720-mi35x (MI350X / MI355X) lmsysorg/sglang:-rocm700-mi30x (MI300X / MI325X)` The model is decode-bound for text and encoder/prefill-bound for vision, so there are two tuned recipes. (The same server handles both; the vision recipe is a safe superset for mixed workloads.) Notes: Text — MI350X / MI355X baseline (native MXFP8) [...] Notes: Text — MI350X / MI355X baseline (native MXFP8) `SGLANG_USE_AITER=1 sglang serve \ --model-path MiniMaxAI/MiniMax-M3 \ --tp 8 --mem-fraction-static 0.80 \ --quantization mxfp8 --dtype bfloat16 \ --chunked-prefill-size 8192 \ --reasoning-parser minimax-m3 --tool-call-parser minimax-m3-nom \ --trust-remote-code --host 0.0.0.0 --port 8080` Text —MI350X / MI355X baseline (native MXFP8) `SGLANG_USE_AITER=
MiniMax (official) on X: "H3 now has Day 0 support in @lmsysorg -- local, customizable, and ready to build on across @NVIDIAAI and @AMD hardware. #MiniMaxH3 #OpenWeights" / Xx.com · supportingLog inSign up ## Post user avatar MiniMax (official) @MiniMax\_AI H3 now has Day 0 support in @lmsysorg -- local, customizable, and ready to build on across @NVIDIAAI and @AMD hardware. #MiniMaxH3 #OpenWeights user avatar LMSYS Org @lmsysorg Aug 3 @MiniMax\_AI H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, 00:00 3:02 AM · Aug 3, 202671.4KViews user avatar SGLang @sgl\_project Aug 3 Go create something with MiniMax H3!!! 211 user avatar Chasen @chasen\_liao Aug 3 [...] 211 user avatar Chasen @chasen\_liao Aug 3 SGLang Diffusion能同时覆盖Blackwell/Hopper和AMD MI300X/MI355X，这种跨厂商Day-0支持很罕见 说明牢Mi 从设计阶段就考虑了硬件多样性，而不只是堆参数。对想做私有化部署的企业来说，这直接降低了锁定风险 点赞 96 user avatar Vector @PrasVector Aug 3 Hey this