TEST #824 RESULTS
05/04/2025 - 3:17 PM
ACCELERATOR
MODEL
65.1
tokens/s
generation
419
ms
time to first token
2981
tokens/s
prompt
774
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
3594
tokens/s
66.6
tokens/s
300
ms
pp4096+tg256
3098
tokens/s
62.5
tokens/s
1.34
sec
pp2048+tg256
3416
tokens/s
67.0
tokens/s
615
ms
pp2048+tg768
3393
tokens/s
65.3
tokens/s
619
ms
pp1024+tg1024
3577
tokens/s
66.5
tokens/s
302
ms
pp1280+tg3072
3494
tokens/s
64.9
tokens/s
381
ms
pp384+tg1152
3541
tokens/s
64.9
tokens/s
124
ms
pp64+tg1024
2153
tokens/s
64.3
tokens/s
45
ms
pp16+tg1536
564
tokens/s
63.5
tokens/s
43
ms