Finally got 3.8-Flash-Next running on my M4Pro 48GB Mac with https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Dense 3.8-27B is just faster... and maybe better due to quantization level... EDIT: Hold a second, Flash-Next is actually performing faster than 27B after some key flags on
