TEST #573 RESULTS
04/08/2025 - 9:30 AM
ACCELERATOR
MODEL
42.9
tokens/s
generation
1.06
sec
time to first token
1178
tokens/s
prompt
363
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
QEMU Virtual CPU version 2.5+
RAM
295GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1458
tokens/s
45.9
tokens/s
725
ms
pp4096+tg256
1220
tokens/s
36.2
tokens/s
3.39
sec
pp2048+tg256
1360
tokens/s
41.9
tokens/s
1.53
sec
pp2048+tg768
1352
tokens/s
40.9
tokens/s
1.54
sec
pp1024+tg1024
1364
tokens/s
43.7
tokens/s
773
ms
pp1280+tg3072
1324
tokens/s
39.0
tokens/s
989
ms
pp384+tg1152
1393
tokens/s
45.4
tokens/s
298
ms
pp64+tg1024
1024
tokens/s
47.1
tokens/s
84
ms
pp16+tg1536
108
tokens/s
46.3
tokens/s
170
ms