CMP 170HX x4 vs DGX Spark
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 Spark44 verified runs · best 86.8 tok/s
| Model | CMP 170HX x4 | DGX Spark |
|---|
| GLM-5.3-Flash | 264.6 W4A16 | 64.1 EXL3 2.05 bpw |
| DeepSeek-V4-Flash-0731 | 92.1 FP8 | — |
| Qwen 3.8 Flash | — | 86.8 EXL3 3.05bpw |
| Qwen3.8-Flash-Next | — | 72.0 EXL3 |
| Qwen3.8-Flash-Next-hibrid48 | — | 60.0 NVFP4 (output head) |
| Qwen3.8-27B | — | 56.0 NVFP4 W4A4 |
| DeepSeek-V4.1-Flash | — | 47.0 FP4 |
Head-to-head (models tested on both): CMP 170HX x4 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