NVIDIA GB10
GPU
122
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Prompt Speed
7578tokens/s
2027tokens/s
Generation Speed
153tokens/s
34.9tokens/s
Time to First Token
207ms
681ms
LocalScore
1777
470
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium