DeepSeek ships V4.1-Flash: asymmetric MoE, 1/4 the KV cache
552B MoE, native vision, 8B/16B active params, MIT weights. The KV-cache compression DeepSeek wants agents to live with.
552B MoE, native vision, 8B/16B active params, MIT weights. The KV-cache compression DeepSeek wants agents to live with.