DeepSeek-V4.1-Flash on 4x DGX Spark: 76 tok/s verified
DeepSeek-V4.1-FlashVerified single-stream run of deepseek-ai/DeepSeek-V4.1-Flash on 4x NVIDIA GB10 (DGX Spark, 512 GB unified, TP4, SGLang, DSPARK spec decoding): 76.0 tok/s decode, 887.6 tok/s prefill, 308.7 ms TTFT, 423 GB unified memory in use, 37.2% draft acceptance.
1 benchmark