Termsslug: engram

Engram

Memory-style parameter module decoupled from the activation path to expand capacity without inference overhead.

Curated Intelligence

2 items · Page 1/1
InfoQ 中文T2·Models
78 pts
Tencent Hunyuan Releases Hy4 Flash at One Twentieth the Cost of Hy4

Tencent Hunyuan released Hy4 Flash, a 224B-parameter (12B activated) multimodal model with 1M context, priced at RMB 0.5 per million input tokens. Through LatentMoE, Engram, 4-bit quantization and megakernel optimizations, its KV cache is one sixth of Hy4's and per-task cost drops to one twentieth, while slightly outperforming the 770B Hy4 preview. Hunyuan plans to open-source it with frequent iterations.

IT之家 · 智能时代T2·Models
78 pts
Tencent Hunyuan Releases Hy4 Flash with 224B Parameters and 5% Task Cost

Tencent Hunyuan officially launched Hy4 Flash, a 224B-parameter model activating 12B per token with multimodal input and 1M-token context. Through coordinated pretraining, post-training and inference optimizations including hybrid attention, LatentMoE, Engram lookup parameters and 4-bit quantization, its per-task cost is just 1/20 of Hy4 and 1/8 of DeepSeek-V4.1-Flash, with official claims of slightly better overall quality than Hy4 preview and plans to open-source.