AMD Radeon 780M Graphics
GPU
13
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
632tokens/s
57tokens/s
Generation Speed
12.0tokens/s
1.9tokens/s
Time to First Token
2.05sec
23.84sec
LocalScore
155
17
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium