Spent two nights getting deepseek-ai/DeepSeek-V4-Flash-0731 (284B MoE, 13B active, native FP4/FP8, 1M context) running production-grade on two DGX Sparks connected by one QSFP DAC cable. Everything — scripts, tuning data, raw benchmarks — is in the repo: https://github.com/raullenchai/twinspark Head
