Looks like a less good version of qwen 30b3a which makes sense bc it is slightly smaller. If they can keep that effiency going into the large one it'll be sick.

Trinity Large [will be] a 420B parameter model with 13B active parameters. Just perfect for a large Ram pool @ q4.

Trinity Nano Preview: 6B parameter MoE (1B active, ~800M non-embedding), 56 layers, 128 experts with 8 active per token

Trinity Mini: 26B parameter MoE (3B active), fully post-trained reasoning model

They did pretraining on their own and are still training the large version on 2048 B300 GPUs

A moe model you say? How kawaii is it? uwu