NVIDIA GeForce RTX 3090
GPU
24
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
13376tokens/s
3605tokens/s
1955tokens/s
Generation Speed
260tokens/s
98.2tokens/s
56.3tokens/s
Time to First Token
101ms
544ms
655ms
LocalScore
3226
973
552
COMPARE MODELS
22 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
Gemma 3 1b It
Q4_K - Medium
Llama 3.2 1B Instruct
Q6_K