📢 Official AMA Announcement The complete MiniMax‑H3 development team will hold an Ask‑Me‑Anything session inside r/StableDiffusion. The main researcher team will be here! - dacongya (Head of H3 Researcher) - Luigi (H3 Researcher) - Nero (H3 Researcher) - Kiro (H3 Researcher) - Reynor (H3 system engineer) - Ryanlee (Head of Devrel) Time: PT 7:00 AM - 8:00 AM Beijing: 22:00 - 23:00 Eastern Time: 10:00 - 11:00 AM Central Europe: 16:00 - 17:00

📢 Official AMA Announcement The complete MiniMax‑H3 development team will hold an Ask‑Me‑Anything session inside r/StableDiffusion. The main researcher team will be here! - dacongya (Head of H3 Researcher) - Luigi (H3 Researcher) - Nero (H3 Researcher) - Kiro (H3 Researcher) - Reynor (Inference Optimization Engineer) - Ryanlee (Head of Devrel) Time: PT 7:00 AM - 8:00 AM Beijing: 22:00 - 23:00 Eastern Time: 10:00 - 11:00 AM Central Europe: 16:00 - 17:00

None of this was us. Day 1 (and the first 48 hours) belonged to the open-source community: Generate with it @ComfyUI — native support + official quantized builds, Day 0 Diffusers — the reference Python pipeline, Day 0 @deepbeepmeep — WanGP v12.41, the 5-6 GB ultra-low VRAM path, Day 1 @pipenetwork — Phosphene + MiniMax-H3-MLX (one-click Mac app + MLX engine), Day 1 @blizaine — Maestro v1.5.5 (one-click GUI + prompt enhancer), Day 2 @ModelScope2022 — DiffSynth-Studio NF4, drops floor to 7-8 GB, Day 2 Serve it @sgl_project — SGLang Diffusion, official cookbook (2×5090 / RTX 6000), Day 0 @vllm_project — vLLM-Omni, OpenAI-compatible video endpoint, Day 0 Train it @ostrisai — AI Toolkit, first trainer (T2V + I2V) 14 h after release, Day 1 @ModelScope2022 — DiffSynth-Studio training scripts (NF4 low-memory), Day 2 @kohya_tech — Musubi Tuner, third trainer (48 GB → shrinking), Day 2 the first community LoRAs running on pruned INT8, Day 2 Speed it up @nvidia SANA team — Sol Engine, 3.95× end-to-end, no quality trade-off, Day 1 sol-attn · sage-attn · EasyCache — 20-35 % each on consumer cards (and they stack), Day 1 Spectrum acceleration — ~34 % Euler sampling time in ComfyUI, Day 2 @AMD — Day 0 support on Instinct MI300X / MI355X (ROCm + SGLang) Extend what it can do Multishot workflow — chains past the 15 s limit up to 30 s with audio, Day 2 Or just run it without installing @MiniMax_AI offical API @fal · @OpenRouter · official API — hosted from launch, $0.13/s for 2K, Day 0 @wavespeed_ai · @runpod — $0.07-0.15 per clip on rented 5090s, Day 2 And everyone who benchmarked, quantized (rockerBOO NVFP4, joeygambino GGUF…), and shared numbers: @umiyuki_ai @luta_ai @onigirikila @ivanfioravanti @Spectromachina and many more 🤗 This is what open weights are for.

We just dropped SOTA open weights for our MiniMax‑H3 video model, and so much happened in 48 hours. The community ran H3 on untested hardware ($280 gaming GPUs, fully‑offline MacBooks) and built brand‑new unplanned tooling. Extremely glad we open‑sourced the weights. Community creations thread 🧵 Hardware requirements are surprisingly modest. Users validated H3 works within 24h on: • $280 RTX 3060 (12GB) • 16‑GB VRAM cards • RTX 4090 / RTX 5090 A year ago, this‑quality video generation was only available via cloud APIs. Now a mid‑range gaming PC is your starting bar.

About Licence: This regional carve-out stems from our ongoing generative video copyright litigation with major @Hollywood studios. We aim to deliver our AI tools globally to all users responsibly. US-based persons looking to deploy MiniMax-H3 may submit formal licensing requests. Licenses will be issued to applicants who commit to implementing robust compliance controls and guardrails fully aligned with US legal, compliance and regulatory requirements.

Thanks for asking about MiniMax-H3 US access limits. This regional carve-out stems from our ongoing generative video copyright litigation with major Hollywood studios. We aim to deliver our AI tools globally to all users responsibly. US-based persons looking to deploy MiniMax-H3 may submit formal licensing requests. Licenses will be issued to applicants who commit to implementing robust compliance controls and guardrails fully aligned with US legal, compliance and regulatory requirements.

I’m incredibly excited to share this: MiniMax has just closed a new $2B funding round. 🚀 At the same time, our CEO, IO, shared three long-term commitments with the team: • No salary until we achieve AGI. • Over the next four years, he will dedicate shares equivalent to 4% of the company’s total equity from his personal holdings to reward employees who are building MiniMax for the long term. • Another 1% will be committed to supporting the open-source community. The funding is exciting. But what excites me even more is what it represents: a long-term commitment to AGI, to our people, and to the open-source ecosystem. We’re living through one of the most exciting moments in the history of AI, and we’re just getting started. If you’re passionate about frontier AI, open source, and building the future, we’d love to build with you. Intelligence with Everyone. 🚀

Hey everyone — our high-performance MSA kernel library is now open-source. The M3 weights are expected to drop this Friday. Thanks for waiting! Github: Paper：

MiniMax-M3 now is rank #8# on @ArtificialAnlys. Due to the workload involved in open-sourcing the MSA operator in parallel, the weights will be released to everyone late next week.

Really glad to meet the @NVIDIAAI team in China. Looking forward to deeper collaboration between @MiniMax_AI and @nvidia on inference optimization for next-generation models. BTW, a quick preview: MiniMax’s latest sparse solution is coming soon. 🥰