DGX Spark x2 vs RTX 3090 x1
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
DGX Spark x215 verified runs · best 474.0 tok/s
RTX 3090 x11 verified run · best 28.1 tok/s
| Model | DGX Spark x2 | RTX 3090 x1 |
|---|
| Qwen3.8-Flash-Next-hibrid48 | 474.0 NVFP4 (output head) | — |
| DeepSeek-V4.1-Flash | 154.0 EXL3 2.9bpw | — |
| Qwen3.8-Flash-Next | 80.0 NVFP4 | — |
| GLM-5.3-Flash | 46.3 NVFP4 | 28.1 EXL3 3.05 bpw |
Head-to-head (models tested on both): DGX Spark x2 1 · RTX 3090 x1 0 · tied 0 · data as of Oct 1, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board