TEST #46 RESULTS
03/28/2025 - 6:59 PM
ACCELERATOR
MODEL
29.2
tokens/s
generation
1.65
sec
time to first token
799
tokens/s
prompt
242
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7402P 24-Core Processor (znver2)
RAM
251.6GB
OS
Linux
Kernel Release
5.15.0-86-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
914
tokens/s
30.5
tokens/s
1.15
sec
pp4096+tg256
754
tokens/s
25.7
tokens/s
5.47
sec
pp2048+tg256
847
tokens/s
28.6
tokens/s
2.45
sec
pp2048+tg768
846
tokens/s
28.1
tokens/s
2.45
sec
pp1024+tg1024
908
tokens/s
29.6
tokens/s
1.16
sec
pp1280+tg3072
886
tokens/s
27.6
tokens/s
1.48
sec
pp384+tg1152
951
tokens/s
30.5
tokens/s
436
ms
pp64+tg1024
800
tokens/s
31.3
tokens/s
131
ms
pp16+tg1536
288
tokens/s
30.9
tokens/s
86
ms