TEST #1932 RESULTS
12/12/2025 - 12:48 PM
ACCELERATOR
MODEL
18.8
tokens/s
generation
1.19
sec
time to first token
1149
tokens/s
prompt
263
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.7GB
OS
Linux
Kernel Release
6.11.0-1014-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #14-Ubuntu SMP PREEMPT_DYNAMIC Thu Aug 14 18:27:36 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1422
tokens/s
19.0
tokens/s
775
ms
pp4096+tg256
999
tokens/s
17.1
tokens/s
4.16
sec
pp2048+tg256
1253
tokens/s
18.9
tokens/s
1.69
sec
pp2048+tg768
1244
tokens/s
18.4
tokens/s
1.70
sec
pp1024+tg1024
1409
tokens/s
19.5
tokens/s
783
ms
pp1280+tg3072
1361
tokens/s
17.9
tokens/s
993
ms
pp384+tg1152
1568
tokens/s
19.5
tokens/s
299
ms
pp64+tg1024
856
tokens/s
19.4
tokens/s
150
ms
pp16+tg1536
228
tokens/s
19.5
tokens/s
123
ms