TEST #115 RESULTS
03/28/2025 - 9:53 PM
ACCELERATOR
MODEL
42.2
tokens/s
generation
1.21
sec
time to first token
962
tokens/s
prompt
323
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7K62 48-Core Processor (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
5.15.0-124-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #134-Ubuntu SMP Fri Sep 27 20:20:17 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1265
tokens/s
45.1
tokens/s
832
ms
pp4096+tg256
1081
tokens/s
36.5
tokens/s
3.82
sec
pp2048+tg256
1208
tokens/s
41.5
tokens/s
1.72
sec
pp2048+tg768
1203
tokens/s
40.9
tokens/s
1.73
sec
pp1024+tg1024
1272
tokens/s
43.7
tokens/s
828
ms
pp1280+tg3072
1126
tokens/s
38.9
tokens/s
1.16
sec
pp384+tg1152
981
tokens/s
43.8
tokens/s
414
ms
pp64+tg1024
260
tokens/s
45.0
tokens/s
280
ms
pp16+tg1536
260
tokens/s
44.5
tokens/s
83
ms