TEST #856 RESULTS
05/11/2025 - 5:08 PM
ACCELERATOR
MODEL
50.6
tokens/s
generation
1.10
sec
time to first token
1533
tokens/s
prompt
413
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 0.5B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-1260P (alderlake)
RAM
31.7GB
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
1893
tokens/s
63.2
tokens/s
558
ms
pp4096+tg256
874
tokens/s
30.3
tokens/s
4.72
sec
pp2048+tg256
1389
tokens/s
41.7
tokens/s
1.50
sec
pp2048+tg768
1377
tokens/s
37.4
tokens/s
1.51
sec
pp1024+tg1024
1821
tokens/s
48.4
tokens/s
580
ms
pp1280+tg3072
1667
tokens/s
33.7
tokens/s
791
ms
pp384+tg1152
2201
tokens/s
60.9
tokens/s
187
ms
pp64+tg1024
1578
tokens/s
73.5
tokens/s
50
ms
pp16+tg1536
996
tokens/s
66.6
tokens/s
25
ms