AIMarkTechPostabout 2 hours ago
DeepSeek Releases V4.1-Flash with 1M Context
5 min read
DeepSeek AI released DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts model with a 1M-token context window. The model activates 8B parameters per token during prefill and 16B during decode, achieving a global KV cache footprint of 890 bytes per token.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
