It's exceptionally optimized... 890 bytes per token. At standard 32K context, that's less than 30MB.

1. https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash

2. https://www.mindstudio.ai/blog/deepseek-v4-1-flash-specs-arc...

yeah they mention:

> Required for a complete inference service (not included in this release):

> A KV cache system

> VE/Prefill/Decode disaggregation (most required engine functionality is already implemented)

> Load balancing across data-parallel replicas for both prefill and decode