MODEL REFERENCE / deepseek-ai
deepseek-ai/DeepSeek-V4.1-Flash
DeepSeek V4.1 Flash vision-language MoE (552B backbone; 8B active per prompt token, 16B per output token) combining sliding-window plus compressed sparse attention with a two-level indexer, engram n-gram memory, hyper-connections, and a DSpark multi-token draft head.
1M context at 8-16B active parameters, with engram n-gram memory
View on HuggingFace
View on ModelScope02 / Configure
Configure serving
Choose engine, hardware and deployment options. The command updates as you go.
03 / Understand