GMKtec EVO-X3 128GB / 2TB vs GMKtec EVO-X2 128GB / 2TB
Prices, stock and measured speed side by side. Last checked 2026-10-16.
Verdict
GMKtec EVO-X2 128GB / 2TB is cheaper in USD by $150 (4%). In EUR, GMKtec EVO-X2 128GB / 2TB is cheaper by €100. Both use the same chip, and we have one public gpt-oss-120b result for that chip, so measured large-model speed is the same. Decide on price, stock, ports and support. Per dollar, GMKtec EVO-X2 128GB / 2TB gives more large-model speed (14.4 vs 13.9 tok/s per $1k).
Generated from the numbers below; no hands-on testing.
| GMKtec EVO-X3 128GB / 2TB | GMKtec EVO-X2 128GB / 2TB | |
|---|---|---|
| Price (USD) | $3,800 | $3,650 |
| Price (EUR) | €3,550 | €3,450 |
| Memory | 128GB | 128GB |
| Stock | in stock | in stock |
| gpt-oss-120b tok/s | 52.74 | 52.74 |
| gpt-oss-120b tok/s per $1k | 13.9 | 14.4 |
| gpt-oss-120b tok/s per €1k | 14.9 | 15.3 |
| Llama-2 7B tok/s | 50.95 | 50.95 |
| Llama-2 7B tok/s per $1k | 13.4 | 14.0 |
| Llama-2 7B tok/s per €1k | 14.4 | 14.8 |
| Stores | US store · EU (GMKtec EU store) | US store · EU (GMKtec EU store) |
Benchmark sources
- GMKtec EVO-X3 128GB / 2TB: large-model source (llama.cpp Vulkan, llama-bench tg32 (comment in thread)) · small-model source
- GMKtec EVO-X2 128GB / 2TB: 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.