TEST #2313 RESULTS
01/16/2026 - 2:39 PM
ACCELERATOR
MODEL
9.2
tokens/s
generation
40.80
sec
time to first token
34
tokens/s
prompt
20
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 265K (arrowlake-s)
RAM
31.4GB
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
35
tokens/s
9.3
tokens/s
29.27
sec
pp4096+tg256
31
tokens/s
7.7
tokens/s
133.06
sec
pp2048+tg256
33
tokens/s
9.0
tokens/s
62.04
sec
pp2048+tg768
33
tokens/s
9.1
tokens/s
62.12
sec
pp1024+tg1024
34
tokens/s
9.0
tokens/s
30.12
sec
pp1280+tg3072
34
tokens/s
8.9
tokens/s
38.13
sec
pp384+tg1152
39
tokens/s
10.0
tokens/s
9.95
sec
pp64+tg1024
35
tokens/s
10.1
tokens/s
1.92
sec
pp16+tg1536
33
tokens/s
9.6
tokens/s
593
ms