MiniMax M3.1 428B Flash

User benchmarks MiniMax-M3.1-Flash 428B at 22.9 t/s decode and 2,567 tok/s prefill at 64K context on 8x NVIDIA A40 with TensorSharp. Setup is TensorSharp with Unsloth UD-Q4_K_XL GGUF (232.3 GiB of model files), F16 KV cache, layer splitting, and speculative decoding disabled. Against Unsloth's llama.cpp support branch on the same files, 64K prefill was 262 tok/s and decode 15.4 t/s; short-chat decode was nearly tied at 26.3 vs 26.0 t/s. Tensor parallelism reached about 41 t/s short-chat decode, and DSpark with confidence gating raised mean generation from 22.9 to 32.3 t/s.