What I ran: 8x B300 on Modal, $56.79 per hour, vLLM, tensor parallel 8, native MXFP4 Cold boot ~27 min (1.56 TB load, JIT, 51 CUDA graph captures) TTFT 0.92 to 1.02 s, decode 92 tok/s steady, 83 tok/s average over 4 prompts $190 per million output tokens. One clean run is about $36 of GPU time. Left
