AIKDnuggetsabout 1 hour ago
DeepSeek Releases Efficient Open Model V4.1-Flash
1 min read
DeepSeek has released DeepSeek-V4.1-Flash, a 552B-parameter Mixture-of-Experts model with a 1-million-token context window. It uses a new Causal Encoder-Decoder architecture to activate only 8B parameters during prefill and 16B during decoding. The model reduces its global KV cache to 890 bytes per token, aiming to make long-context AI inference significantly cheaper and more efficient for running agents.
Level
Hype check
Tap to vote and see what everyone thinks.
