Hy4 Preview reduced to 214 GB with 1.25-bit quantization
A Tencent publication says Sherry quantization reduces Hy4 Preview from 1.5 TB to 214 GB at 1.25 bits per weight, and describes running the model on GPUs distributed across multiple machines.
In a publication dated September 1, 2026, Tencent says Sherry quantization reduces Hy4 Preview from 1.5 TB to 214 GB, using 1.25 bits per weight. The text also describes running the model on GPUs distributed across multiple machines. These details are relevant to readers exploring lower-memory inference and multi-machine GPU configurations.
To assess the result, consult the original publication and check its stated conditions, figures, and technical context; do not assume that a smaller model size alone guarantees particular performance or quality. If you use AI to study or apply the material, avoid submitting personal data or internal documents without authorization, and check your organization’s policy.