llamaperf

RTX 6000 vs RTX A6000 48GB

For running local LLMs · 7 reports across 3 models

Side A
RTX 6000
Vendor
nvidia
VRAM
48GB
Memory
Discrete
Side B
RTX A6000 48GB
Vendor
nvidia
VRAM
48GB
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 →

ModelRTX 6000RTX A6000 48GB
DeepSeek V4 Flashup to 285B128.6n=217.2n=1
Qwen3.8up to 2400B150.0n=3
Gemma 4up to 31B16.9n=1

More comparisons