DeepSeek V4.1 Flash 1017 · Comparison

Comparison of DeepSeek models generating a pagoda

창작자 설명

Same prompt, same 2 DGX Sparks, same speed. -DeepSeek V4.1 Flash: 46,355 tokens, 20.6 min -V4.1 Flash 1017: 38,146 tokens, 16.9 min 18% fewer tokens for the same pagoda. Both 37.6 tok/s, thinking on, no output cap. EXL3 2.9bpw quants by @Libertai_DAI (1017) @deepseek_ai