Home
Latest Results
Download
About
Blog
Gemma 3 12b
Q4_0
12.8B
params
COMPARE ACCELERATORS
1 accelerators tested
Select Accelerators
Quadro RTX 6000
24GB
Gemma 3 12b - Q4_0
Prompt tokens/s
Generation tokens/s
Time to First Token (ms)
LocalScore
LEADERBOARD
GPU
CPU+GPU
CPU
ACCELERATOR
PROMPT
GENERATION
TTFT
LOCALSCORE
Quadro RTX 6000
GPU / 24GB
PROMPT
1380
tokens/s
GENERATION
39.9
tokens/s
TTFT
904
ms
LOCALSCORE
393