TEST #3513 RESULTS
05/11/2026 - 10:30 PM
ACCELERATOR
MODEL
33.2
tokens/s
generation
1.23
sec
time to first token
1052
tokens/s
prompt
305
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
1263
tokens/s
34.9
tokens/s
839
ms
pp4096+tg256
1024
tokens/s
30.5
tokens/s
4.03
sec
pp2048+tg256
1153
tokens/s
33.0
tokens/s
1.81
sec
pp2048+tg768
1136
tokens/s
32.4
tokens/s
1.83
sec
pp1024+tg1024
1205
tokens/s
33.5
tokens/s
880
ms
pp1280+tg3072
1150
tokens/s
31.5
tokens/s
1.14
sec
pp384+tg1152
1237
tokens/s
34.2
tokens/s
339
ms
pp64+tg1024
994
tokens/s
34.6
tokens/s
112
ms
pp16+tg1536
310
tokens/s
34.3
tokens/s
79
ms