MiniMax H3
RuntimeWire's continuing coverage of MiniMax's H3 model family — launches, benchmarks, and the competitive fallout.
All updates
- MiniMax will present H3 at ModCon in San Francisco on August 18 — Morgan Suo will discuss MiniMax's multimodal video model at Modular's San Francisco conference for AI infrastructure developers.
- Magnific will showcase MiniMax H3 at a San Francisco creator event — The live San Francisco presentation puts H3 before Magnific's claimed 1 million subscribers, though the event materials do not establish a product rollout.
- Head to head: Kandinsky5 vs MiniMax H3 Reference to Video — One model kept landing the brief; the other kept drifting into adjacent, less specific scenes.
- MiniMax and fal announce livestream on building with H3 video model — The planned session will feature speakers from MiniMax and fal discussing how developers are using H3's multimodal video capabilities, though its date and registration details…
- MiniMax posts guessing-game teaser without a verifiable product link — The Shanghai AI company asked viewers to identify a subject in inaccessible media, leaving no verifiable connection to H3 or another product.
- MiniMax plans to release H3 2K model and sparse-attention code — MiniMax says it plans to release H3's separate 2K regeneration model and sparse-attention reference code, giving developers more of its video-generation stack to inspect and test…
- MiniMax schedules H3 consumer-hardware demo as performance remains unverified — The August 7 session promises open H3 weights, stereo audio and ready-made workflows, but no official benchmark yet identifies the hardware, memory use or generation speed.
- MiniMax brings H3 video generation to Luma Agents, with access terms unclear — MiniMax's H3 video model is available through Luma's multi-model creative product, while pricing, eligibility, regional availability and developer access remain undocumented.
- MiniMax H3 draws local apps and training tools within 48 hours — Maestro added desktop support as developers pushed H3 onto a gaming GPU and offline Macs beyond MiniMax's tested setups.
- ComfyUI ships editable MiniMax H3 graphs for local video workflows — Yannik Marek's node-based engine added native MiniMax H3 workflows, giving creators inspectable graphs for the open-weight video model.
- MiniMax publishes H3 checkpoints as 2K workflow still requires hosted services — The 288 GB Hugging Face release adds two downloadable base checkpoints, while the complete 2K workflow still uses hosted MiniMax services.
- MiniMax launches H3 2K video model with promised open weights — MiniMax launched H3 with 2K video and native stereo audio. MiniMax says the weights are coming in days, but the H3 license and official local hardware requirements remained…
- Argil adds MiniMax H3 to its AI-avatar social video workflow — Founders Laodis Menard and Brivael Le Pogam are placing MiniMax's video model inside Argil's production system for avatars, scripts, captions, B-roll and finished social clips.
- MiniMax teases H3 as a unified multimodal model for Hailuo AI — MiniMax is framing H3 as a single system for text, images, video and sound, aimed at carrying creative context across media.