Tencent Hy· @TencentHunyuan · X·· 2026-08-29AI 评分62
AI 导读
腾讯混元将 Hy4-preview（770B 参数、49B 激活、1M 上下文）从 1.5TB 压缩至约 200GiB GGUF 格式，通过 MIX-STQ1_0 混合量化按层分配位宽（最低 1.31-bit STQ1_0，最高 2.06-bit IQ2_XXS）。
正文 · 原文
We compressed Hy4-preview from 1.5TB to ～200GiB GGUF and it still works well !
Meet MIX-STQ1_0.The trick isn’t just going low, it’s deciding where: calibration data picks each layer’s bit-width, some down to 1.31-bit STQ1_0, some up to 2.06-bit IQ2_XXS. Same budget, lower error.
Accuracy barely moves vs BF16
📊 MCP Atlas 83.7→83.2
📊 SWE-Bench multi 82.9→81.3
📊 MRCR 81.3→81.1
📊 IFBench 73.5→72.5
See the details on HF : AngelSlim/Hy4-preview-GGUF
Weights & low-bit GGUFs 👇
https://huggingface.co/AngelSlim/Hy4-preview-GGUF
#LLM #Quantization #llamacpp #Hy
🚀 Hy4 preview is here. 770B, 49B active, 1M context. Built for productivity. Open source frontier. Consistent affordable price. Use it. Tell us what breaks. More on Hy blog：https://hy.tencent.ai/research/hy4-preview HuggingFace：https://huggingface.co/tencent/Hy4-preview Github：https://github.com/Tencent-Hunyuan/Hy4-preview在 X 查看被引用的帖子
来源：Tencent Hy · x.com