TEST #784 RESULTS
04/29/2025 - 6:54 PM
ACCELERATOR
MODEL
20.9
tokens/s
generation
8.17
sec
time to first token
171
tokens/s
prompt
76
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9454P 48-Core Processor (znver4)
RAM
251.4GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
177
tokens/s
21.9
tokens/s
5.85
sec
pp4096+tg256
151
tokens/s
18.8
tokens/s
27.15
sec
pp2048+tg256
167
tokens/s
20.5
tokens/s
12.32
sec
pp2048+tg768
167
tokens/s
20.2
tokens/s
12.32
sec
pp1024+tg1024
176
tokens/s
21.3
tokens/s
5.86
sec
pp1280+tg3072
175
tokens/s
19.9
tokens/s
7.37
sec
pp384+tg1152
183
tokens/s
21.8
tokens/s
2.14
sec
pp64+tg1024
188
tokens/s
22.0
tokens/s
385
ms
pp16+tg1536
159
tokens/s
21.9
tokens/s
145
ms