NVIDIA GeForce GTX 1060 3GB
GPU
3
GB
PERFORMANCE OVERVIEW
Model
Qwen2.5 0.5B Instruct
Q4_K - Medium630M
tinyllama_tinyllama-1.1b-chat-v1.0
Q4_K - Medium1.1B
DeepSeek R1 Distill Qwen 1.5B
IQ4_XS - 4.25 bpw1.8B
Prompt Speed
3114tokens/s
1509tokens/s
106tokens/s
Generation Speed
98.7tokens/s
71.4tokens/s
8.4tokens/s
Time to First Token
437ms
919ms
11.94sec
LocalScore
889
489
42
COMPARE MODELS
3 models tested
Select Models
Qwen2.5 0.5B Instruct
Q4_K - Medium
tinyllama_tinyllama-1.1b-chat-v1.0
Q4_K - Medium
DeepSeek R1 Distill Qwen 1.5B
IQ4_XS - 4.25 bpw
