Shipping MiniMax H3 three days after the weights dropped
MiniMax released the open weights for H3, their omni-modal video model, on August 3. By August 6 it was running in production on our own GPUs — text-to-video and image-to-video, with joint audio, served through gen-image, the imference API and Imference Desktop. We’re two developers working on this part-time. This post is about the unglamorous middle: what it actually takes to serve a frontier video model three days after the weights drop, when you don’t write custom kernels and don’t have a lab’s GPU budget. ...