TEST #825 RESULTS
05/04/2025 - 3:31 PM
ACCELERATOR
MODEL
30.4
tokens/s
generation
1.18
sec
time to first token
1075
tokens/s
prompt
303
LocalScore
HOW YOU STACK UP
Explore All ResultsGemma 3 12b It Qat - Q4_0
SYSTEM
CPU
11th Gen Intel Core i7-11700F @ 2.50GHz (rocketlake)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1253
tokens/s
32.3
tokens/s
848
ms
pp4096+tg256
1086
tokens/s
27.5
tokens/s
3.81
sec
pp2048+tg256
1188
tokens/s
30.5
tokens/s
1.76
sec
pp2048+tg768
1189
tokens/s
29.2
tokens/s
1.76
sec
pp1024+tg1024
1249
tokens/s
30.4
tokens/s
851
ms
pp1280+tg3072
1224
tokens/s
29.2
tokens/s
1.08
sec
pp384+tg1152
1231
tokens/s
31.8
tokens/s
344
ms
pp64+tg1024
949
tokens/s
31.5
tokens/s
97
ms
pp16+tg1536
306
tokens/s
31.4
tokens/s
85
ms