TEST #151 RESULTS
03/28/2025 - 10:26 PM
ACCELERATOR
MODEL
27.0
tokens/s
generation
1.15
sec
time to first token
1205
tokens/s
prompt
305
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7K62 48-Core Processor (znver2)
RAM
503.5GB
OS
Linux
Kernel Release
5.15.0-122-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #132-Ubuntu SMP Thu Aug 29 13:45:52 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1494
tokens/s
27.9
tokens/s
721
ms
pp4096+tg256
1026
tokens/s
24.8
tokens/s
4.03
sec
pp2048+tg256
1074
tokens/s
26.7
tokens/s
1.94
sec
pp2048+tg768
1346
tokens/s
26.5
tokens/s
1.56
sec
pp1024+tg1024
1496
tokens/s
27.3
tokens/s
721
ms
pp1280+tg3072
1460
tokens/s
26.0
tokens/s
913
ms
pp384+tg1152
1653
tokens/s
27.9
tokens/s
268
ms
pp64+tg1024
1004
tokens/s
28.3
tokens/s
139
ms
pp16+tg1536
294
tokens/s
28.0
tokens/s
89
ms