Unsloth can now run prompts on a schedule against a local or API model, and it supports MiniMax-M3.1-Flash (428B mixture-of-expertsA model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.Full definition →, 23B active) and FLUX 3 image editing. Mac performance also improved.
Terms in this piece · Glossary
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
