NVIDIA GeForce RTX 4070 Ti SUPER
GPU
16
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
13268tokens/s
3561tokens/s
2147tokens/s
Generation Speed
161tokens/s
53.9tokens/s
36.8tokens/s
Time to First Token
104ms
364ms
617ms
LocalScore
2738
808
505
COMPARE MODELS
3 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