Tesla P40
GPU
24
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
LLaMA v2
Q4_06.7B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
2209tokens/s
833tokens/s
292tokens/s
Generation Speed
90.5tokens/s
40.9tokens/s
13.6tokens/s
Time to First Token
656ms
1.52sec
4.02sec
LocalScore
700
282
100
COMPARE MODELS
4 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium
LLaMA v2
Q4_0
Qwen3-Coder-30B-A3B-Instruct-1M
Q4_K - Medium