Nunchux has deployed MiniMax-H3 on AMD MI355X. On 8 GPUs, inference is up to 26.7× faster than SGLang. ⚡️A 5-second clip takes 1.3 seconds. With streaming generation, you can even modify the prompt while the video is playing to guide the next frames.

Nunchux is live at We’re building the frontier of multimodal generative AI inference: fast, affordable, high-quality serving for image, video, and world models. Our Modelverse brings 30+ image, video, and avatar models behind one API. Use Nunchux-optimized models in Radical Speed and Radical Value tiers, alongside partner APIs. More models are on the way. We’re opening access through the waitlist now. New accounts get $10 in credits. Read our launch blog:

NUNCHUK ON COLDCARD VULNERABILITY Some Nunchuk platform keys were generated with a Coldcard Mk4, but the company says those keys are never used directly. Instead, it derives separate keys through custom logic, making them less susceptible to lookup-table attacks based on compromised Coldcard seeds. Nunchuk adds that, given enough time, it assumes attackers could eventually include those derived keys as well.