NVIDIA GB10
GPU
120
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
7529tokens/s
2035tokens/s
1108tokens/s
Generation Speed
112tokens/s
33.2tokens/s
18.3tokens/s
Time to First Token
205ms
679ms
1.23sec
LocalScore
1604
463
254
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium