NVIDIA GeForce RTX 3080
GPU
10
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
11601tokens/s
2996tokens/s
1236tokens/s
Generation Speed
229tokens/s
80.6tokens/s
38.3tokens/s
Time to First Token
117ms
426ms
4.38sec
LocalScore
2813
826
299
COMPARE MODELS
4 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
Llama 3 8b Bnb 4bit
Q4_K - Medium