NVIDIA GeForce RTX 4050 Laptop GPU
GPU
6
GB
PERFORMANCE OVERVIEW
Model
tinyllama_tinyllama-1.1b-chat-v1.0
Q8_01.1B
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Falcon3 Mamba 7B Instruct
Q4_07.3B
Prompt Speed
3987tokens/s
4979tokens/s
83tokens/s
Generation Speed
99.5tokens/s
114tokens/s
14.7tokens/s
Time to First Token
410ms
286ms
15.52sec
LocalScore
989
1255
43
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
tinyllama_tinyllama-1.1b-chat-v1.0
Q8_0
Falcon3 Mamba 7B Instruct
Q4_0