DeepSeek releases DeepSeek-V4.1-Flash
DeepSeek-V4.1-Flash released — a multimodal MoE with a 552B backbone and a 1M-token context that activates only 16B parameters per token during decode and 8B during prefill. With Compressed Sparse Attention 2 (CSA2), an FP4 KV cache and SWA Bounded Replay, it cut the global KV cache to 890 bytes per token (about 1/4 of DeepSeek-V4-Flash) and the persistently stored KV footprint to about 1/8. It was pretrained on a 45T-token multimodal corpus, and the company claims it performs substantially better than the baseline despite the smaller cache.
Why it matters
A case of pushing the diagnosis that the bottleneck for agent workloads has shifted from compute to KV-cache storage and bandwidth through the entire model design. Using different active parameters for prefill and decode is especially new.
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2609.19969Added in Week 39, 2026 · See that week