NVIDIA GeForce RTX 4070
GPU
12
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
12717tokens/s
3192tokens/s
1697tokens/s
Generation Speed
283tokens/s
76.3tokens/s
38.8tokens/s
Time to First Token
112ms
415ms
775ms
LocalScore
3179
838
440
COMPARE MODELS
5 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
Gemma 3 12b It
Q3_K - Large
Cogito v1 Preview Qwen 14B
Q4_K - Medium