Dell Pro Max / Pro Precision with GB10 vs NVIDIA DGX Spark
Prices, stock and measured speed side by side. Last checked 2026-10-16.
Verdict
NVIDIA DGX Spark is cheaper in USD by $1,204 (26%). In EUR, NVIDIA DGX Spark is cheaper by €1,070 (at least one EUR price is converted). 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, NVIDIA DGX Spark gives more large-model speed (12.5 vs 9.9 tok/s per $1k).
Generated from the numbers below; no hands-on testing.
| Dell Pro Max / Pro Precision with GB10, 128GB / 2TB | NVIDIA DGX Spark (Founders Edition) | |
|---|---|---|
| Price (USD) | $5,903 | $4,699 |
| Price (EUR) | ≈€5,246 | ≈€4,176 |
| Memory | 128GB | 128GB |
| Stock | not tracked shop | not tracked shop |
| gpt-oss-120b tok/s | 58.72 | 58.72 |
| gpt-oss-120b tok/s per $1k | 9.9 | 12.5 |
| gpt-oss-120b tok/s per €1k | 11.2 | 14.1 |
| Llama-2 7B tok/s | 57.21 | 57.21 |
| Llama-2 7B tok/s per $1k | 9.7 | 12.2 |
| Llama-2 7B tok/s per €1k | 10.9 | 13.7 |
| Stores | US store · EU store | US store · EU store |
Benchmark sources
- Dell Pro Max / Pro Precision with GB10: large-model source (llama.cpp CUDA, llama-bench tg32, b7946) · small-model source
- NVIDIA DGX Spark: large-model source (llama.cpp CUDA, llama-bench tg32, b7946) · 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.