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
13438tokens/s
3536tokens/s
1944tokens/s
Generation Speed
267tokens/s
95.7tokens/s
55.8tokens/s
Time to First Token
101ms
476ms
661ms
LocalScore
3266
960
547
COMPARE MODELS
23 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