TEST #1937 RESULTS
12/13/2025 - 10:22 PM
ACCELERATOR
MODEL
19.3
tokens/s
generation
2.50
sec
time to first token
499
tokens/s
prompt
157
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
47.8GB
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
608
tokens/s
20.7
tokens/s
1.73
sec
pp4096+tg256
514
tokens/s
17.8
tokens/s
8.03
sec
pp2048+tg256
571
tokens/s
19.4
tokens/s
3.64
sec
pp2048+tg768
566
tokens/s
19.0
tokens/s
3.67
sec
pp1024+tg1024
585
tokens/s
19.5
tokens/s
1.80
sec
pp1280+tg3072
564
tokens/s
17.9
tokens/s
2.32
sec
pp384+tg1152
432
tokens/s
19.9
tokens/s
938
ms
pp64+tg1024
492
tokens/s
20.0
tokens/s
205
ms
pp16+tg1536
161
tokens/s
19.6
tokens/s
146
ms