NVIDIA H100 80GB HBM3
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
14608tokens/s
4687tokens/s
2609tokens/s
Generation Speed
96.2tokens/s
42.4tokens/s
23.4tokens/s
Time to First Token
91ms
263ms
475ms
LocalScore
2490
911
505
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