TEST #1241 RESULTS
07/23/2025 - 9:19 AM
ACCELERATOR
MODEL
33.6
tokens/s
generation
1.20
sec
time to first token
1076
tokens/s
prompt
311
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v3 @ 2.30GHz (haswell)
RAM
62.8GB
OS
Linux
Kernel Release
6.15.7-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 17 Jul 2025 21:05:29 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1310
tokens/s
35.4
tokens/s
810
ms
pp4096+tg256
1052
tokens/s
31.0
tokens/s
3.93
sec
pp2048+tg256
1192
tokens/s
33.5
tokens/s
1.75
sec
pp2048+tg768
1179
tokens/s
32.8
tokens/s
1.77
sec
pp1024+tg1024
1244
tokens/s
33.9
tokens/s
852
ms
pp1280+tg3072
1192
tokens/s
31.9
tokens/s
1.10
sec
pp384+tg1152
1291
tokens/s
34.5
tokens/s
326
ms
pp64+tg1024
953
tokens/s
34.9
tokens/s
155
ms
pp16+tg1536
274
tokens/s
34.7
tokens/s
86
ms