MiniMax H3 adds open weights, stereo audio and 15-second 2K video generation
petrusenko_max · x · 2026-08-04
MiniMax H3 is launched with open weights and native stereo audio. The model can generate up to 15-second 2K video clips from text, images, video, or audio inputs in a single pass.
The post also says H3 is natively supported in ComfyUI and can run locally on an Nvidia 3060, making it notable both as a multimodal generation model and as a relatively accessible local workflow option.
Related event: MiniMax Releases 33B Open-Weight Multimodal Model H3 with Local Deployment(10 posts)→
More from Infra
- SkyRL ships Day-0 RL support for Beam with +62% LoRA decode throughput in vLLM — vllm_project · 2026-10-16
- DFlash2 delivers up to 3.03x decode-only speedup for Beam across five benchmarks — vllm_project · 2026-10-16
- vLLM's Beam serving kernels cut GB200 forward time from 8.15 to 6.47 ms at TP8 batch 128 — vllm_project · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Nemotron 3.5 Bolt runs 16 concurrent streams on a single DGX Spark — NVIDIAAI · 2026-10-16
- Why your computer can't store 0.2: an IEEE 754 primer — Franc0Fernand0 · 2026-10-16