TEST #3550 RESULTS
05/16/2026 - 8:52 AM
ACCELERATOR
MODEL
37.5
tokens/s
generation
1.00
sec
time to first token
1211
tokens/s
prompt
356
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900HX (alderlake)
RAM
15.7GB
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
853
tokens/s
34.4
tokens/s
1.22
sec
pp4096+tg256
1415
tokens/s
35.0
tokens/s
2.93
sec
pp2048+tg256
1601
tokens/s
36.5
tokens/s
1.31
sec
pp2048+tg768
1601
tokens/s
37.1
tokens/s
1.31
sec
pp1024+tg1024
1154
tokens/s
38.8
tokens/s
919
ms
pp1280+tg3072
1632
tokens/s
36.9
tokens/s
811
ms
pp384+tg1152
1474
tokens/s
39.2
tokens/s
290
ms
pp64+tg1024
966
tokens/s
39.5
tokens/s
132
ms
pp16+tg1536
207
tokens/s
39.8
tokens/s
105
ms