TEST #74 RESULTS
03/28/2025 - 9:07 PM
ACCELERATOR
MODEL
21.0
tokens/s
generation
1.83
sec
time to first token
733
tokens/s
prompt
203
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7443 24-Core Processor (znver3)
RAM
251.5GB
OS
Linux
Kernel Release
6.8.0-49-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
841
tokens/s
21.7
tokens/s
1.26
sec
pp4096+tg256
675
tokens/s
19.1
tokens/s
6.12
sec
pp2048+tg256
757
tokens/s
20.7
tokens/s
2.75
sec
pp2048+tg768
751
tokens/s
20.5
tokens/s
2.78
sec
pp1024+tg1024
841
tokens/s
21.2
tokens/s
1.26
sec
pp1280+tg3072
823
tokens/s
20.2
tokens/s
1.60
sec
pp384+tg1152
910
tokens/s
21.8
tokens/s
467
ms
pp64+tg1024
763
tokens/s
22.2
tokens/s
144
ms
pp16+tg1536
233
tokens/s
21.9
tokens/s
112
ms