Search results for "Hy4"

Technology 28 Aug 2026

Tencent open-sources Hy4 preview with 770B parameters and 1M-token context

Tencent open-sourced Hy4 preview, a 770B-parameter MoE model with 49B activated weights and a 1M-token context window. The Apache 2.0 release puts a frontier-class model within reach of self-hosted inference stacks.

Technology 03 Sep 2026

Tencent compresses 770B Hy4 MoE model to 214GB GGUF via layer-heterogeneous quantization

Tencent open-sourced an extreme quantized GGUF build of its 770B Hunyuan Hy4 model, compressing 1.5TB weights down to 214GB. By varying precision from 1.31-bit on non-critical layers to 2+ bits on sensitive layers, the model fits on accessible multi-GPU nodes.

Technology 30 Aug 2026

September 2026 AI Watch: Daybreak Lands, Early Model Drops, and Open Threads Update

September’s watch frame: Daybreak keys passed, early drops landed, and Astra moved from Critical designation into a staged Daybreak-first rollout (3 September). Gemini 4 and Apple Intelligence in China remain open threads.