Qwen3.8-27B SLQ Quantized GGUF Files Released with EAR@10 Performance Data

Original title: Statistically Lossless Qwen3.8 27B GGUFs

The Qwen3.8-27B model has been released using customized SLQ (Statistically-Lossless Quantization) technology in GGUF format. Three models, EAR98, EAR98.5, and EAR99, are provided with specific file sizes and EAR@10 performance metrics. EAR measures the probabilistic overlap between the original BF16 model and the quantized tokens.

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.