NVIDIA DGX Spark vs GMKtec EVO-X2 128GB / 1TB
Prices, stock and measured speed side by side. Last checked 2026-10-16.
Verdict
GMKtec EVO-X2 128GB / 1TB is cheaper in USD by $1,199 (34%). In EUR, GMKtec EVO-X2 128GB / 1TB is cheaper by €876 (at least one EUR price is converted). On gpt-oss-120b, NVIDIA DGX Spark is faster (58.72 vs 52.74 tok/s; sources and engines differ, see below). Per dollar, GMKtec EVO-X2 128GB / 1TB gives more large-model speed (15.1 vs 12.5 tok/s per $1k).
Generated from the numbers below; no hands-on testing.
| NVIDIA DGX Spark (Founders Edition) | GMKtec EVO-X2 128GB / 1TB | |
|---|---|---|
| Price (USD) | $4,699 | $3,500 |
| Price (EUR) | ≈€4,176 | €3,300 |
| Memory | 128GB | 128GB |
| Stock | not tracked shop | in stock |
| gpt-oss-120b tok/s | 58.72 | 52.74 |
| gpt-oss-120b tok/s per $1k | 12.5 | 15.1 |
| gpt-oss-120b tok/s per €1k | 14.1 | 16.0 |
| Llama-2 7B tok/s | 57.21 | 50.95 |
| Llama-2 7B tok/s per $1k | 12.2 | 14.6 |
| Llama-2 7B tok/s per €1k | 13.7 | 15.4 |
| Stores | US store · EU store | US store · EU (GMKtec EU store) |
Benchmark sources
- NVIDIA DGX Spark: large-model source (llama.cpp CUDA, llama-bench tg32, b7946) · small-model source
- GMKtec EVO-X2 128GB / 1TB: large-model source (llama.cpp Vulkan, llama-bench tg32 (comment in thread)) · small-model source
Large: gpt-oss-120b MXFP4 (59 GiB weights), text generation tok/s at empty context, single request. Small: llama.cpp llama-bench, Llama-2 7B Q4_0, tg128 (text generation tok/s); best of FA on/off as posted.