DeepSeek Details V4.1-Flash: 552B MoE with Just 8B Active Params on Input
ccerrato147 · x · 2026-09-10
DeepSeek shared architectural details of V4.1-Flash:
- 552B-parameter MoE with an asymmetric design
- New Causal Encoder–Decoder architecture: only 8B active parameters for input, 16B for output
- New pretraining methods plus larger-scale RL post-training deliver benchmark results ahead of flagships including DeepSeek-V4-Pro
More from Models
- GPT-6.1 Terra rolls out to all Plus, Pro, Enterprise and Edu users — OpenAI · 2026-10-27
- OpenAI launches GPT-6.1 Terra with 50% lower API prices than GPT-5.6 Terra — OpenAI · 2026-10-27
- GPT-6.1 Terra API pricing revealed: $1 input / $5 output, $0.05 cached — airesearch12 · 2026-10-27
- In cyber, intention matters little: Chintala on model info leaks, and what users should do — brhydon · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27