TEST #1871 RESULTS
11/26/2025 - 1:50 PM
ACCELERATOR
MODEL
17.6
tokens/s
generation
1.26
sec
time to first token
1072
tokens/s
prompt
247
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.6GB
OS
Linux
Kernel Release
6.14.0-1013-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #13-Ubuntu SMP PREEMPT_DYNAMIC Wed Oct 29 06:01:19 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1367
tokens/s
18.1
tokens/s
802
ms
pp4096+tg256
943
tokens/s
16.3
tokens/s
4.41
sec
pp2048+tg256
1180
tokens/s
17.6
tokens/s
1.79
sec
pp2048+tg768
1178
tokens/s
17.1
tokens/s
1.80
sec
pp1024+tg1024
1306
tokens/s
17.7
tokens/s
843
ms
pp1280+tg3072
1228
tokens/s
16.8
tokens/s
1.10
sec
pp384+tg1152
1427
tokens/s
18.2
tokens/s
327
ms
pp64+tg1024
766
tokens/s
18.5
tokens/s
157
ms
pp16+tg1536
249
tokens/s
18.4
tokens/s
118
ms