# 腾讯混元 Hy4-preview 压缩至 200GiB 精度几乎无损

- 来源：Tencent Hy (@TencentHunyuan)
- 发布时间：2026-08-29 13:31
- AIHOT 分数：62
- AIHOT 链接：https://aihot.news/items/cmtdyzaj70acfro2mp5n5il12
- 原文链接：https://x.com/TencentHunyuan/status/2093572224342954019

## AI 摘要

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

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

### 引用推文

> Tencent 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. Mo...