Topic · h3-series

MiniMax H3 Series: from open weights to 35x throughput

Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.

7 articles·Aug 2, 2026 — Aug 30, 2026·3.4k total views
diffusionefficiency··393

FastH3 Open-Sources a 4-Step MiniMax H3: Up to 14x on One B200

FastVideo open-sources FastH3 Preview v1: DMD2 distillation cuts MiniMax H3's 49 DiT calls to 4, plus 90% sparse attention — up to 14x on…

h3-seriesinference··356

fal's H3 Max: post-trained MiniMax H3 makes 5s clips in 3s

fal's H3 Max: post-trained MiniMax H3 makes 5s clips in ~3s, ~35x official throughput, #1 in preference and Design Arena evals; capped at…

ai-inferenceh3-series··187

MiniMax H3 tested: open weights differ from the API model

After MiniMax H3's weights landed on Hugging Face on August 3, community testing revealed that the open-source release only ships the base…

h3-seriesmodel-release··206

MiniMax H3's first landing: Meitu RoboNeo tests editability

On August 3, Meitu's RoboNeo announced its integration with MiniMax's newly open-sourced multimodal generation model MiniMax H3, focusing…

h3-seriesmodel-release··212

MiniMax H3 unifies generation, reference, and editing

MiniMax has introduced H3, a general-purpose omni-modal video model that accepts text, images, video and audio in one context and generates…

ai-inferenceh3-series··1.9k

ComfyUI runs MiniMax H3 on day one: 2K video generation on RTX 3060

On 3 August 2026 MiniMax released the open-weights MiniMax H3 (Hailuo 3.0) omni-modal video model, and ComfyUI shipped Day-0 support that…

h3-serieshardware··219

MiniMax H3 runs on MTT S5000 in three hours: software stack wins

On the day MiniMax open-sourced H3, Moore Threads said it achieved stable deployment on a single eight-card MTT S5000 node in only three…