DeepSeek introduced DeepSeek-V4.1-Flash—the smallest model in its new family with native vision. It is a 552B MoE with a Causal Encoder–Decoder (8B active on input, 16B on output), claims benchmarks ahead of flagships including V4-Pro, shrinks KV cache to ~1/4 HBM and ~1/8 SSD vs prior gen, and published HF weights plus a tech report.

Key Takeaways

  • ✓DeepSeek-V4.1-Flash launches: smallest in new family with native vision.
  • ✓552B MoE Causal Encoder–Decoder (8B in / 16B out active); claims wins vs flagships incl. V4-Pro.
  • ✓KV cache ~1/4 HBM and ~1/8 SSD; HF weights and tech report published.
ADSponsored