DGX Spark x2 vs RTX 3090 x8
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
DGX Spark x210 verified runs · best 474.0 tok/s
RTX 3090 x84 verified runs · best 91.2 tok/s
| Model | DGX Spark x2 | RTX 3090 x8 |
|---|
| Qwen3.8-Flash-Next-hibrid48 | 474.0 NVFP4 (output head) | — |
| DeepSeek-V4.1-Flash | 154.0 EXL3 2.9bpw | — |
| DeepSeek-V4-Flash-0731 | — | 91.2 FP8_E4M3 |
| Qwen3.8-Flash-Next | 80.0 NVFP4 | — |
| GLM-5.3-Flash | 46.3 NVFP4 | 75.2 AWQ-4bit |
| keys-DeepSeekV4Flash-Vision-EXP-ablit | — | 66.8 FP8 |
Head-to-head (models tested on both): DGX Spark x2 0 · RTX 3090 x8 1 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board