CMP 170HX x2 vs DGX Spark
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
CMP 170HX x25 verified runs · best 186.9 tok/s
DGX Spark44 verified runs · best 86.8 tok/s
| Model | CMP 170HX x2 | DGX Spark |
|---|
| Qwen3.8-Flash-Next | 186.9 W4A16-FP8PLE | 72.0 EXL3 |
| Qwen 3.8 Flash | — | 86.8 EXL3 3.05bpw |
| GLM-5.3-Flash | — | 64.1 EXL3 2.05 bpw |
| Laguna-S-2.1 | 63.3 Q4_K_M | — |
| Hy-MT2-30B-A3B | 61.4 FP8 | — |
| Qwen3.8-Flash-Next-hibrid48 | — | 60.0 NVFP4 (output head) |
| Qwen3.8-27B | — | 56.0 NVFP4 W4A4 |
| DeepSeek-V4.1-Flash | — | 47.0 FP4 |
| Hy3 | 27.6 Q2_K_XL | — |
| Baichuan-M3-235B | 26.1 Q3_K_M | — |
Head-to-head (models tested on both): CMP 170HX x2 1 · DGX Spark 0 · tied 0 · data as of Sep 25, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board