Tencent Hunyuan Releases Hy4 flash, Supporting Office Tasks at About One-Twentieth the Per-Task Cost of Hy4

Written by

in

Tencent Hunyuan releases the Hy4 flash model, with a total parameter count of 224B and 12B activated per token. It supports a 1M-token context and multimodal processing.

Source:explainx.ai · Read original

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *