腾讯Hy4 preview可通过Sherry量化方法从1.5TB压缩至214GB，权重仅需1.25比特，精度几乎不受影响。量化版GGUF和原版模型均已开放下载。
RT @ivanfioravanti: Sherry quantization method by Tencent, combined with large Hy4 Preview is able to deliver incredible results! 1.5TB to 214GB using 1.25 bits weights while keeping incredible accuracy! BF16 vs Sherry: - MCP Atlas 83.7→83.2 - SWE-Bench multi 82.9→81.3 - MRCR 81.3→81.1 - IFBench 73.5→72.5
1.5TB → 214GB. Seven times smaller, barely a dent. That's Hy4 preview. The trick is Sherry — our quantization method that packs weights down to 1.25 bits each. (The image shows how.) It also unlocks a new way to run it: stitch the GPUs you already have across machines, and they work as one. GGUF (quantized): https://t.co/EC2ZYpVnC4 Original model: https://t.co/olB85l7dxy
