TEST #423 RESULTS
04/06/2025 - 8:31 PM
ACCELERATOR
MODEL
19.9
tokens/s
generation
1.16
sec
time to first token
1133
tokens/s
prompt
269
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9554 64-Core Processor (znver4)
RAM
43GB
OS
Linux
Kernel Release
5.15.0-136-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #147-Ubuntu SMP Sat Mar 15 15:53:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1423
tokens/s
21.9
tokens/s
770
ms
pp4096+tg256
1050
tokens/s
16.0
tokens/s
3.97
sec
pp2048+tg256
1253
tokens/s
19.2
tokens/s
1.69
sec
pp2048+tg768
1254
tokens/s
18.6
tokens/s
1.69
sec
pp1024+tg1024
1419
tokens/s
20.3
tokens/s
773
ms
pp1280+tg3072
1341
tokens/s
17.8
tokens/s
1.01
sec
pp384+tg1152
1461
tokens/s
21.4
tokens/s
315
ms
pp64+tg1024
753
tokens/s
22.1
tokens/s
127
ms
pp16+tg1536
243
tokens/s
21.7
tokens/s
110
ms