NVIDIA GeForce RTX 3070
GPU
8
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
8063tokens/s
2006tokens/s
398tokens/s
Generation Speed
216tokens/s
59.6tokens/s
5.6tokens/s
Time to First Token
180ms
710ms
6.59sec
LocalScore
2140
560
71
COMPARE MODELS
7 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
DeepSeek R1 Distill Llama 8B
Q6_K
Qwen3 0.6B
Q8_0