DGX Spark GB10 Grace Blackwell, 128GB vs NVIDIA RTX PRO 6000 Blackwell, 96GB for local AI
Both hold 40 of the 49 current models here. The DGX Spark, 128GB costs $13,301 less, though the RTX PRO 6000 Blackwell, 96GB is priced as the card alone, without the PC around it. On Qwen3.8 27B, the strongest model both hold, the RTX PRO 6000 Blackwell, 96GB is about 7.1× faster: 78 tok/s against 11, both estimated from memory bandwidth. The DGX Spark, 128GB pays for itself sooner, in 346 years against 1,071 years at 500k tokens a day.
| DGX Spark GB10 Grace Blackwell, 128GB | NVIDIA RTX PRO 6000 Blackwell, 96GB | |
|---|---|---|
| Price | $4,699 | $18,000card only |
| Memory | 128 GB | 96 GB |
| Usable by the GPU | 119.5 GB | 95 GB |
| Memory bandwidth | 273 GB/s | 1792 GB/s |
| Power under load | 150 W | 600 W |
| Models that fit | 40 | 40 |
| Best model it runs | Qwen3.8 27B | Qwen3.8 27B |
| Speed on that model | 11 tok/s estimated | 78 tok/s estimated |
| Pay-back on that model | Pays back in 346 years | Pays back in 1,071 years |
Run the numbers on the DGX Spark GB10 Grace Blackwell, 128GB · or the NVIDIA RTX PRO 6000 Blackwell, 96GB
How much use it takes to pay back
Everything above is at 500k tokens a day. Pay-back moves with how much you actually run, so here are both machines on Qwen3.8 27B, the strongest model both hold, at the five levels of use the calculator names. The DGX Spark GB10 Grace Blackwell, 128GB pays back sooner at every level of use, so this is not a choice that turns on how hard you work it.
| A day's use | DGX Spark GB10 Grace Blackwell, 128GB | NVIDIA RTX PRO 6000 Blackwell, 96GB |
|---|---|---|
| 50ka few chats a day | 3,456 years | 10,715 years |
| 200klight assistant use | 864 years | 2,679 years |
| 1Ma moderate coding-assistant day | 173 years | 536 years |
| 4Mheavy coding with an agent | 43 years | 134 years |
| 20Magents running most of the day | 11 yearsits ceiling | 27 years |
On Qwen3.8 27B the DGX Spark GB10 Grace Blackwell, 128GB generates at most 15.2M tokens a day, so its figure at 20M tokens a day is for the most it can do, not for the whole of what was asked.
Run the DGX Spark GB10 Grace Blackwell, 128GB at 20M tokens a day · or the NVIDIA RTX PRO 6000 Blackwell, 96GB
The same models, not to the same length
Every model on this list that fits one machine fits the other at 32k of context, so memory does not change what they run. What it changes is how far you can take the context on one of them. The DGX Spark GB10 Grace Blackwell, 128GB has 119.5 GB usable against 95 GB, and spare memory is what the KV cache grows into as you keep more tokens.
| Model | DGX Spark GB10 Grace Blackwell, 128GB | NVIDIA RTX PRO 6000 Blackwell, 96GB |
|---|---|---|
| Devstral 2 123B75 GB of weights | 64k | 32k |
Each figure is the longest context the calculator offers that the machine still holds that model at, and no model is taken past its own context limit. The other 48 models the calculator counts reach the same length on both machines, at every setting from 4k to 256k.
Run Devstral 2 123B on the DGX Spark GB10 Grace Blackwell, 128GB at 64k · or on the NVIDIA RTX PRO 6000 Blackwell, 96GB at 32k
The DGX Spark, 128GB is also head to head with another computer: Mac mini M5 Pro, 24GB · Mac Studio M5 Max, 128GB · GMKtec EVO-X2, 128GB · MacBook Air M5 (15-inch), 16GB · MacBook Pro M5 Pro (16-inch), 64GB · Corsair AI Workstation 300, 128GB. With a graphics card: Radeon AI PRO R9700, 32GB.
The RTX PRO 6000 Blackwell, 96GB is also head to head with another card: Radeon AI PRO R9700, 32GB · GeForce RTX 5090, 32GB · GeForce RTX 4090, 24GB · GeForce RTX 3090, 24GB · GeForce RTX 4080, 16GB · GeForce RTX 3060, 12GB. With a complete computer: Mac mini M5 Pro, 24GB · Mac Studio M5 Max, 128GB · GMKtec EVO-X2, 128GB · MacBook Air M5 (15-inch), 16GB · MacBook Pro M5 Pro (16-inch), 64GB.
The assumptions behind both columns
Both columns use the same usage: 500k tokens a day at 15:1 input to output, 32k of context, $0.17 per kWh, and today's API prices held flat. Speeds marked estimated are worked out from memory bandwidth rather than measured, and pay-back scales with them. The RTX PRO 6000 Blackwell, 96GB is priced as the card alone, so add the PC around it before comparing it with a complete computer. All seven cards here are ranked by what each one holds. Change any of it in the calculator.
More head to head: everything the DGX Spark GB10 Grace Blackwell, 128GB runs · everything the NVIDIA RTX PRO 6000 Blackwell, 96GB runs · every other match-up · the quickest pay-back at each level of use · every model against the frontier