TEST #1063 RESULTS
06/16/2025 - 1:14 AM
ACCELERATOR
MODEL
19.7
tokens/s
generation
2.41
sec
time to first token
531
tokens/s
prompt
163
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E3-1245 v5 @ 3.50GHz (skylake)
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
624
tokens/s
20.9
tokens/s
1.69
sec
pp4096+tg256
522
tokens/s
17.7
tokens/s
7.91
sec
pp2048+tg256
580
tokens/s
19.6
tokens/s
3.58
sec
pp2048+tg768
581
tokens/s
19.3
tokens/s
3.58
sec
pp1024+tg1024
606
tokens/s
20.0
tokens/s
1.74
sec
pp1280+tg3072
591
tokens/s
18.6
tokens/s
2.21
sec
pp384+tg1152
603
tokens/s
20.3
tokens/s
685
ms
pp64+tg1024
485
tokens/s
20.7
tokens/s
209
ms
pp16+tg1536
190
tokens/s
20.4
tokens/s
130
ms