A 774B multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition →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 → in FP8 lowers the memory needed to self-host a frontier-scale open model. It ships with vLLM and SGLang serving paths, under a custom Tencent license that needs checking before use.
Terms in this piece · Glossary
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
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.