NVIDIA DGX Spark vs Dell Pro Precision with GB10
The cheapest Dell Pro Precision with GB10 lists for about $824 more than the cheapest NVIDIA DGX Spark. Rows where the two differ are tinted.
NVIDIA GB10
NVIDIA DGX Spark
NVIDIA's own GB10 desktop with 128GB of unified memory, CUDA and a ConnectX-7 port for linking up to four units. Its 273 GB/s memory bandwidth limits single-user token speed compared with Macs of similar memory size, while prompt processing is strong.
gpt-oss-20b, 4-bit: 83 tok/s
NVIDIA GB10
Dell Pro Precision with GB10
Dell's GB10 box (model FCM1253, first sold as Dell Pro Max with GB10), with 128GB, DGX OS and Dell support options. It runs the same software as the DGX Spark and differs in price, storage choices, power adapter and warranty.
gpt-oss-20b, 4-bit: 83 tok/s
| Specification | NVIDIA DGX Spark | Dell Pro Precision with GB10 |
|---|---|---|
| Kind | NVIDIA GB10 · NVIDIA | NVIDIA GB10 · Dell |
| Chip or GPUs | GB10 Grace Blackwell | GB10 Grace Blackwell |
| Memory | 128 GB | 128 GB |
| Memory for models | 120 GB (GPU-usable memory)assumption | 120 GB (GPU-usable memory)assumption |
| Memory bandwidth | 273 GB/s | 273 GB/s |
| Price | ~$4,699 | ~$5,523 |
| Largest at 4-bit, 8k context | Qwen3.8 Flash-Next | Qwen3.8 Flash-Next |
| Software | CUDA, Vulkan | CUDA, Vulkan |
| Power | 240 W | 280 W |
What each one runs
Every model in the catalog that at least one of the two holds at 4-bit with 8,192 tokens of context. Copper speeds are measured medians; outlined ones are estimates. Rows where only one fits, or where the speed differs by more than a quarter, are tinted.
| Model | NVIDIA DGX Spark | Dell Pro Precision with GB10 |
|---|---|---|
| Qwen3.8 Flash-Next125B, 6B active · 111.4 GB file | ~22–29 tok/sestimate | ~22–29 tok/sestimate |
| Nemotron 3 Super 120B-A12B120B, 12B active · 81.0 GB file | 17 tok/smedian of 2 runs | 17 tok/smedian of 2 runs |
| Qwen3.5 122B-A10B122B, 10B active · 71.3 GB file | 21 tok/smedian of 2 runs | 21 tok/smedian of 2 runs |
| Mistral Medium 3.5 128B128B · 69.8 GB file | ~2.5–3.0 tok/sestimate | ~2.5–3.0 tok/sestimate |
| GLM-4.5-Air106B, 12B active · 68.0 GB file | ~16–20 tok/sestimate | ~16–20 tok/sestimate |
| Mistral Small 4 119B (2603)119B, 6.5B active · 67.6 GB file | ~32–41 tok/sestimate | ~32–41 tok/sestimate |
| Llama 4 Scout 17B-16E Instruct109B, 17B active · 60.9 GB file | ~13–16 tok/sestimate | ~13–16 tok/sestimate |
| gpt-oss-120b117B, 5.1B active · 58.5 GB file | 53 tok/smedian of 23 runs | 53 tok/smedian of 23 runs |
| Qwen3 Coder Next80B, 3B active · 45.2 GB file | 49 tok/smedian of 2 runs | 49 tok/smedian of 2 runs |
| Llama 3.3 70B Instruct70B · 39.6 GB file | ~4.4–5.2 tok/sestimate | ~4.4–5.2 tok/sestimate |
| Nemotron 3.5 Lightning 30B-A3B30B, 3B active · 23.7 GB file | ~50–64 tok/sestimate | ~50–64 tok/sestimate |
| Qwen3.6 35B-A3B35B, 3B active · 20.8 GB file | ~67–86 tok/sestimate | ~67–86 tok/sestimate |
| Ornith 1.5 35B-A3B35B, 3B active · 20.2 GB file | ~69–88 tok/sestimate | ~69–88 tok/sestimate |
| Qwen3 Coder 30B-A3B Instruct30.5B, 3.3B active · 17.3 GB file | ~64–82 tok/sestimate | ~64–82 tok/sestimate |
| Gemma 4 31B IT30.7B · 17.1 GB file | ~10–12 tok/sestimate | ~10–12 tok/sestimate |
| Granite 4.2 30B29.3B · 16.8 GB file | ~10–12 tok/sestimate | ~10–12 tok/sestimate |
| Qwen3.8 27B27B · 16.2 GB file | ~11–13 tok/sestimate | ~11–13 tok/sestimate |
| Gemma 4 26B-A4B IT25.2B, 3.8B active · 15.9 GB file | ~50–64 tok/sestimate | ~50–64 tok/sestimate |
| Qwen3.6 27B27B · 15.7 GB file | ~11–13 tok/sestimate | ~11–13 tok/sestimate |
| Devstral Small 2 24B (2512)24B · 13.3 GB file | ~13–15 tok/sestimate | ~13–15 tok/sestimate |
| gpt-oss-20b21B, 3.6B active · 10.8 GB file | 83 tok/smedian of 13 runs | 83 tok/smedian of 13 runs |
| Phi-414.7B · 8.3 GB file | ~21–25 tok/sestimate | ~21–25 tok/sestimate |
| Ministral 3 14B Reasoning (2512)13.9B · 7.7 GB file | ~22–27 tok/sestimate | ~22–27 tok/sestimate |
| Gemma 4 12B IT11.95B · 6.6 GB file | ~26–31 tok/sestimate | ~26–31 tok/sestimate |
| Qwen3.5 9B9B · 5.3 GB file | ~33–39 tok/sestimate | ~33–39 tok/sestimate |
| Granite 4.2 8B8.8B · 5.2 GB file | ~33–40 tok/sestimate | ~33–40 tok/sestimate |
| Gemma 4 E4B IT8B · 5.0 GB file | ~61–73 tok/sestimate | ~61–73 tok/sestimate |
| Qwen3 8B8.2B · 4.7 GB file | ~37–44 tok/sestimate | ~37–44 tok/sestimate |
| Llama 3.1 8B Instruct8B · 4.6 GB file | 38 tok/smedian of 5 runs | 38 tok/smedian of 5 runs |
| Qwen3.5 4B4B · 2.6 GB file | ~68–81 tok/sestimate | ~68–81 tok/sestimate |
Full pages: NVIDIA DGX Spark · Dell Pro Precision with GB10 · check a different quant or context length