AIAI Tech Engine
Home/Benchmarks/DGX Spark vs EVO-X3: Flash-Next same-prompt bench
#DGX Spark#EVO-X3#Flash-Next#ROCmFP4#NVFP4#bench

DGX Spark vs EVO-X3: Flash-Next same-prompt bench

DGX Spark (NVFP4/SGLang) vs EVO-X3 (ROCmFP4/Vulkan) on Flash-Next with the same Angry Birds and 3D architecture HTML prompts. Decode ~37 vs ~27.5 tok/s.

AIAI Tech Engine Lab
Independent lab measurement
SPONSORED / ADVERTISEMENT
예약된 광고 영역

Bottom line. Compare boxes, not model tabs: DGX Spark ↔ EVO-X3. Today: one filled cell — Flash-Next, same prompts. Decode: Spark ~37 tok/s · EVO ~27.5 tok/s (~75%). Prefill TTFT on arch3d: EVO 1.69s vs Spark 8.84s. Stacks differ (NVFP4+SGLang vs ROCmFP4+Vulkan) — read as hardware tendency, not identical-binary A/B.

Two boxes

NVIDIA DGX Spark · GB10 · ~128GB UMA

Flash-Next NVFP4 · SGLang. Same protocol as the prior Spark Flash cell.

arch3d 37.3 tok/s · angry 36.7 tok/s.

GMKtec EVO-X3 · Ryzen AI MAX+ 395 · Radeon 8060S · ~120GB GTT

ROCmFP4-FAST GGUF · Laurent llama.cpp Vulkan RADV · :8081

arch3d 27.5 tok/s · angry 27.6 tok/s · TTFT arch 1.69s.

Same prompts · Flash-Next speed

taskSpark TTFTEVO TTFTSpark decodeEVO decodeEVO/Spark
arch3d (≤12k)8.84s1.69s37.327.5~74%
angry (≤7k)1.06s1.19s36.727.6~75%

3D architecture HTML

DGX Spark · HTML
Spark Flash-Next arch3d
EVO-X3 · HTML
EVO Flash-Next arch3d

Angry Birds HTML

DGX Spark · HTML
Spark angry
EVO-X3 · HTML
EVO angry

What to pick (Flash-Next only)

GoalPick
decode tok/sDGX Spark
AMD Strix Halo–class local + ROCmFP4 pathEVO-X3
Model choice on Sparkthree-model post

Empty cells

  • EVO Qwen3.8-27B ROCmFP4 + DFlash2 (redownloading)
  • EVO DeepSeek-V4-Flash Q3-ROCmFP4 (split tensor count mismatch)