llamaperf

DGX Spark vs RTX Pro 6000 Blackwell

For running local LLMs · 52 reports across 13 models

Side A
DGX Spark
Vendor
nvidia
VRAM
128GB
Memory
Unified
Side B
RTX Pro 6000 Blackwell
Vendor
nvidia
VRAM
96GB
Memory
Discrete

Highest reported generation speed by model family

These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →

ModelDGX SparkRTX Pro 6000 Blackwell
Qwen3.8up to 2400B181.0n=4177.0n=13
DeepSeek V4 Flashup to 285B90.0n=1045.0n=4
Qwen3.6up to 35Bn=1n=4
Ling-3.0up to 124B40.9n=4
Museup to 30B37.0n=157.0n=2
GLM-5.2up to 744B24.0n=2
Aurora1.0up to 0Bn=1
DeepSeek V3n=1
GLM-5.1n=1
Kimi K320.0n=1
Llama 3.2up to 1Bn=1
Mimo 2.5n=1
Tencent-HY3up to 295B57.4n=1

More comparisons