TEST #2593 RESULTS
02/10/2026 - 5:51 PM
ACCELERATOR
MODEL
6.2
tokens/s
generation
5.10
sec
time to first token
420
tokens/s
prompt
80
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700KF (alderlake)
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
239
tokens/s
5.7
tokens/s
4.47
sec
pp4096+tg256
145
tokens/s
3.6
tokens/s
28.60
sec
pp2048+tg256
615
tokens/s
6.5
tokens/s
3.48
sec
pp2048+tg768
600
tokens/s
6.3
tokens/s
3.57
sec
pp1024+tg1024
633
tokens/s
6.7
tokens/s
1.77
sec
pp1280+tg3072
578
tokens/s
5.8
tokens/s
2.38
sec
pp384+tg1152
583
tokens/s
6.8
tokens/s
831
ms
pp64+tg1024
315
tokens/s
7.2
tokens/s
472
ms
pp16+tg1536
75
tokens/s
6.9
tokens/s
367
ms