DGX Spark x2 vs Intel Arc Pro B70
Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.
DGX Spark x218 sourced runs · best 474.0 tok/s
Intel Arc Pro B7018 verified runs · best 283.1 tok/s
| Model | DGX Spark x2 | Intel Arc Pro B70 |
|---|---|---|
| Qwen3.8-Flash-Next-hibrid48 | 474.0 | — |
| Laguna-XS-2.1 | — | 283.1 |
| Qwen3.6-35B-A3B | — | 248.3 |
| Ornith-1.0-35B-B70-Turbo | — | 224.9 |
| Nex-N2-mini-B70-Turbo | — | 224.3 |
| SIQ-1-35B-B70-Turbo | — | 223.7 |
| Qwen-AgentWorld-35B-A3B-B70-Turbo | — | 209.0 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | — | 186.6 |
| DeepSeek-V4.1-Flash | 154.0 | — |
| LFM2.5-2.6B | — | 132.4 |
| Ornith-1.5-35B-A3B | — | 131.5 |
| Qwen3.8-Flash-Next | 93.0 | 24.0 |
| Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP | — | 58.4 |
| Ornith-1.5-9B | — | 49.6 |
| GLM-5.3-Flash | 46.3 | — |
| Qwen3.6-27B-MTP | — | 36.0 |
| Muse-Glimmer-30B | — | 29.2 |
| ThinkingCap-Qwen3.6-27B | — | 27.9 |
| Qwen3.8-27B | — | 27.8 |