TEST #3514 RESULTS
05/11/2026 - 10:35 PM
ACCELERATOR
MODEL
33.1
tokens/s
generation
1.24
sec
time to first token
1050
tokens/s
prompt
304
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7251 8-Core Processor
RAM
220.3GB
OS
Linux
Kernel Release
6.17.0-23-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #23~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 14 16:11:48 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1258
tokens/s
34.8
tokens/s
843
ms
pp4096+tg256
1021
tokens/s
30.3
tokens/s
4.05
sec
pp2048+tg256
1139
tokens/s
32.8
tokens/s
1.83
sec
pp2048+tg768
1127
tokens/s
32.3
tokens/s
1.85
sec
pp1024+tg1024
1196
tokens/s
33.3
tokens/s
887
ms
pp1280+tg3072
1145
tokens/s
31.4
tokens/s
1.15
sec
pp384+tg1152
1241
tokens/s
34.0
tokens/s
338
ms
pp64+tg1024
1002
tokens/s
34.6
tokens/s
111
ms
pp16+tg1536
322
tokens/s
34.3
tokens/s
78
ms