TEST #842 RESULTS
05/07/2025 - 7:06 PM
ACCELERATOR
MODEL
63.0
tokens/s
generation
264
ms
time to first token
4859
tokens/s
prompt
1050
LocalScore
HOW YOU STACK UP
Explore All ResultsGemma 3 4b 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
6150
tokens/s
64.6
tokens/s
182
ms
pp4096+tg256
4792
tokens/s
59.0
tokens/s
872
ms
pp2048+tg256
5720
tokens/s
62.3
tokens/s
374
ms
pp2048+tg768
5629
tokens/s
62.2
tokens/s
379
ms
pp1024+tg1024
6113
tokens/s
63.9
tokens/s
183
ms
pp1280+tg3072
5950
tokens/s
61.3
tokens/s
232
ms
pp384+tg1152
6055
tokens/s
64.2
tokens/s
79
ms
pp64+tg1024
2570
tokens/s
64.8
tokens/s
41
ms
pp16+tg1536
754
tokens/s
64.3
tokens/s
38
ms