CMP 170HX x4 vs DGX Spark x2
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
CMP 170HX x42 verified runs · best 264.6 tok/s
DGX Spark x210 verified runs · best 474.0 tok/s
| Model | CMP 170HX x4 | DGX Spark x2 |
|---|
| Qwen3.8-Flash-Next-hibrid48 | — | 474.0 NVFP4 (output head) |
| GLM-5.3-Flash | 264.6 W4A16 | 46.3 NVFP4 |
| DeepSeek-V4.1-Flash | — | 154.0 EXL3 2.9bpw |
| DeepSeek-V4-Flash-0731 | 92.1 FP8 | — |
| Qwen3.8-Flash-Next | — | 80.0 NVFP4 |
Head-to-head (models tested on both): CMP 170HX x4 1 · DGX Spark x2 0 · tied 0 · data as of Sep 25, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board