Practitioners think DeepSeek v4.1-Flash deserved a major version number.

Latent Space's September 12 roundup collects reaction to the causal encoder-decoder release: 763B total parameters, 8B active at prefill and 16B at decode, 1M context, KV cache cut to about 890 bytes per token, roughly one eighth of V4 Pro. Sebastian Raschka argues the architectural break warrants calling it v5. Fraser Price reports 300+ TPS on four RTX Pros at full precision with under 32GB peak system RAM using SSD offloading. TeortaxesTex supplies the counterweight, questioning whether DeepSeek ships internal research artifacts instead of products, and the model is verbose at ~89k tokens per task, 25-62% more than competitors. That verbosity is the number to hold against the KV-cache win before you price a workload.