NVIDIA H100 PCIe
GPU
79
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
18590tokens/s
5202tokens/s
2973tokens/s
Generation Speed
335tokens/s
120tokens/s
72.2tokens/s
Time to First Token
68ms
236ms
417ms
LocalScore
4512
1382
802
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