NVIDIA GeForce GTX 1660 SUPER
GPU
6
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Llama 3.2 3B Instruct
Q4_K - Medium3.6B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Prompt Speed
825tokens/s
293tokens/s
133tokens/s
Generation Speed
36.5tokens/s
14.4tokens/s
10.0tokens/s
Time to First Token
1.75sec
4.99sec
10.58sec
LocalScore
258
95
50
COMPARE MODELS
9 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Llama 3.2 3B Instruct
Q4_K - Medium
Qwen2.5 Coder 7B Instruct
Q4_K - Medium
Qwen2.5 0.5B Instruct
Q4_K - Medium