NVIDIA H100 NVL
GPU
93
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
13164tokens/s
4299tokens/s
2351tokens/s
Generation Speed
83.9tokens/s
37.1tokens/s
20.5tokens/s
Time to First Token
99ms
289ms
529ms
LocalScore
2232
820
450
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