DeepSeek V4 Flash 285B (13B active) Vision-Exp

User reports DeepSeek V4 Flash Vision-Exp at 31.7 tok/s decode on a Mac Studio M4 Max 128GB. Setup is ds4 (DwarfStar) with IQ2_XXS/Q2_K GGUF, DSpark speculative decoding at confidence 0.6, and a 32768 context length. Thinking-on pagoda run reached 29.84 tok/s over 26,415 completion tokens; 1M context loaded at 97.15 GiB planned total with 32.0 tok/s decode. User notes DSpark adds roughly 10-20% over no speculation.