TEST #60 RESULTS
03/28/2025 - 8:50 PM
ACCELERATOR
MODEL
46.2
tokens/s
generation
713
ms
time to first token
1834
tokens/s
prompt
492
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6342 CPU @ 2.80GHz (icelake-server)
RAM
503.5GB
OS
Linux
Kernel Release
6.8.0-48-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #48~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Oct 7 11:24:13 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2192
tokens/s
47.3
tokens/s
489
ms
pp4096+tg256
1718
tokens/s
41.9
tokens/s
2.41
sec
pp2048+tg256
2013
tokens/s
45.6
tokens/s
1.04
sec
pp2048+tg768
2014
tokens/s
45.1
tokens/s
1.04
sec
pp1024+tg1024
2178
tokens/s
46.8
tokens/s
492
ms
pp1280+tg3072
2118
tokens/s
44.4
tokens/s
626
ms
pp384+tg1152
2241
tokens/s
47.7
tokens/s
207
ms
pp64+tg1024
1607
tokens/s
48.5
tokens/s
60
ms
pp16+tg1536
426
tokens/s
48.1
tokens/s
58
ms