DGX Spark x3
Nvidia · 128 GB VRAM
2recorded runs
152.9best tok/s
2sourced
How it compares — 128 GB per card · multi-GPU
Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.
Evidence: 2 sourced runs · 1 independent source · first recorded Sep 12, 2026 · last recorded Oct 18, 2026. What these labels mean.
All benchmarks Compare DGX Spark x3 →
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| DGX Spark x3 · 128 GB | DeepSeek-V4.1-Flash-1017 | EXL3 3.5bpw | vllm bot-lab-21's EXL3 build + drowzeys' … | 300000 | 152.9 ✓ | — | — | src |
| DGX Spark x3 · 128 GB | DeepSeek-V4.1-Flash | EXL3 3.5bpw | vllm e47aa780b | 300000 | 46.0 ✓ | — | — | src |
Related reading: GPU buying guide · used GPUs · Value index · Street prices