Tencent Hunyuan compresses Hy4-preview to ~200GiB GGUF with MIX-STQ1_0

Tencent Hunyuan announced a quantization method, MIX-STQ1_0, that compresses the Hy4-preview model from 1.5TB to about 200GiB GGUF while maintaining performance.

This update bears on 1 kinds of work in 1 markets. Highest level accepted: L1 Assisted.

Highest accepted

L1Assisted

Work

1

Markets

1

Views

631K

The work it bears on

Highest level first. Open a kind of work to see everything else that moved it.

• L1Assisted
  Develop algorithms and study computational propertiesComputing and engineering research
  L1 AssistedFrom the publisher only

Published at