Huyawo Research uses V4.1 Flash 1017 for open-source architecture and cloud experiments
Huyawo Research runs DeepSeek V4.1 Flash 1017 via DeepSeek Harness and Ollama Cloud for open-source ecosystem architecture, development and cloud experiments, citing strong engineering results and clear per-million-token savings.
I think a lot of people still, quite innocently, underestimate what a Flash model is capable of. In our work at Huyawo Research, we're using DeepSeek V4.1 Flash 1017 (via DeepSeek Harness) to work on the architecture and development of our open-source technology ecosystem, as well as cloud experiments, where it performs exceptionally well. We're using it through Ollama Cloud, and the level of engineering we're able to achieve with it is impressive, not to mention the cost savings per million tokens, which allow us to produce more, produce better, and spend less.