SemiAnalysis(@SemiAnalysis_):Congrats to @deepseek_ai on releasing DeepSeek-V4.1-Flash! > 552B backbone, with a causal encoder-decoder activating just 8B params at prefill, 16B at decode > 196B Engram memory accessed through sparse lookups > ~8x less persistent KV than V4-Flash through bounded replay

2026.09.10 11:56

Congrats to @deepseek_ai on releasing DeepSeek-V4.1-Flash! > 552B backbone, with a causal encoder-decoder activating just 8B params at prefill, 16B at decode > 196B Engram memory accessed through sparse lookups > ~8x less persistent KV than V4-Flash through bounded replay