TEST #3876 RESULTS
07/08/2026 - 4:18 AM
ACCELERATOR
MODEL
46.3
tokens/s
generation
517
ms
time to first token
2476
tokens/s
prompt
605
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900KF (alderlake)
RAM
127.7GB
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
3041
tokens/s
47.6
tokens/s
357
ms
pp4096+tg256
2445
tokens/s
43.1
tokens/s
1.70
sec
pp2048+tg256
2803
tokens/s
47.1
tokens/s
751
ms
pp2048+tg768
2809
tokens/s
44.4
tokens/s
751
ms
pp1024+tg1024
3044
tokens/s
45.9
tokens/s
358
ms
pp1280+tg3072
2912
tokens/s
45.7
tokens/s
465
ms
pp384+tg1152
3128
tokens/s
47.9
tokens/s
156
ms
pp64+tg1024
1630
tokens/s
46.7
tokens/s
61
ms
pp16+tg1536
469
tokens/s
48.5
tokens/s
54
ms