TEST #1233 RESULTS
07/21/2025 - 6:30 AM
ACCELERATOR
MODEL
24.3
tokens/s
generation
1.10
sec
time to first token
1234
tokens/s
prompt
301
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-9900K CPU @ 3.60GHz (skylake)
RAM
63.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1430
tokens/s
25.0
tokens/s
756
ms
pp4096+tg256
1086
tokens/s
22.4
tokens/s
3.82
sec
pp2048+tg256
1313
tokens/s
24.0
tokens/s
1.60
sec
pp2048+tg768
1316
tokens/s
23.8
tokens/s
1.60
sec
pp1024+tg1024
1472
tokens/s
24.5
tokens/s
735
ms
pp1280+tg3072
1437
tokens/s
23.5
tokens/s
931
ms
pp384+tg1152
1623
tokens/s
25.0
tokens/s
276
ms
pp64+tg1024
1113
tokens/s
25.4
tokens/s
114
ms
pp16+tg1536
312
tokens/s
25.2
tokens/s
91
ms