DeepSeek V4 Flash 284B (13B active)

User reports an optimized DeepSeek V4 Flash 8-bit affine MLX model on oMLX, with prefill improving from ~300-321 to ~533 tok/s and decode from ~7.31 to ~20-22 tok/s. Real runs at 79K-119K context show 19.2-20.7 tok/s. User asks for community review on accuracy and next optimization directions.