KQuant - new quantization technique, 3.7× better quants for Qwen Flash Next 180B, Qwen 27B, 35B, 9B (measured in KL-divergence reduction) (MLX)
hey folks, im Alish, an ml engineer from Nace (folks behind Drex, an open source decision family model that hit #1 in Artificial analysis in decision index 2.1).