Accelerator icon
NVIDIA RTX PRO 6000 Blackwell Server Edition
GPU
95
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
18081tokens/s
2581tokens/s
Generation Speed
106tokens/s
17.9tokens/s
Time to First Token
74ms
637ms
LocalScore
2962
438
COMPARE MODELS

2 models tested

Select Models

Llama 3.2 1B Instruct

Q4_K - Medium

Qwen2.5 14B Instruct

Q4_K - Medium

NVIDIA RTX PRO 6000 Blackwell Server Edition - 95GB