kld

A new EXL3 quant of Qwen3.8-27B by yeasah achieves the lowest KLD (0.0002) among competitors while requiring only 18.8 GiB of VRAM for weights, outperforming quants from Unsloth and turboderp.

The author maps the Kullback-Leibler divergence of KV cache quantization for the Qwen3.6-35B-A3B and Gemma4-E2B QAT models.

A detailed benchmark comparing KV cache quantization methods (TurboQuant, TCQ, q4, q5, q8) using PPL and KLD metrics on Qwen 3.6 27B, finding that TCQ improves low-bit quantization, asymmetric KV beats symmetric at same size, and q8 is often overkill. Includes analysis and data in linked article.