TEST #1995 RESULTS
12/20/2025 - 11:51 PM
ACCELERATOR
MODEL
53.2
tokens/s
generation
665
ms
time to first token
1882
tokens/s
prompt
532
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-8700 CPU @ 3.20GHz (skylake)
RAM
15.8GB
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
2238
tokens/s
54.6
tokens/s
476
ms
pp4096+tg256
1928
tokens/s
48.4
tokens/s
2.15
sec
pp2048+tg256
2148
tokens/s
52.7
tokens/s
973
ms
pp2048+tg768
2147
tokens/s
52.0
tokens/s
973
ms
pp1024+tg1024
2301
tokens/s
53.7
tokens/s
466
ms
pp1280+tg3072
2112
tokens/s
50.9
tokens/s
626
ms
pp384+tg1152
2266
tokens/s
55.0
tokens/s
201
ms
pp64+tg1024
1404
tokens/s
56.2
tokens/s
63
ms
pp16+tg1536
392
tokens/s
55.5
tokens/s
58
ms