Search

Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.