TEST #113 RESULTS
03/28/2025 - 9:50 PM
ACCELERATOR
MODEL
20.5
tokens/s
generation
5.71
sec
time to first token
204
tokens/s
prompt
90
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6138 CPU @ 2.00GHz (skylake-avx512)
RAM
376.5GB
OS
Linux
Kernel Release
6.8.0-45-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #45~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Sep 11 15:25:05 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
246
tokens/s
21.4
tokens/s
4.21
sec
pp4096+tg256
231
tokens/s
17.8
tokens/s
17.75
sec
pp2048+tg256
240
tokens/s
20.0
tokens/s
8.57
sec
pp2048+tg768
241
tokens/s
19.7
tokens/s
8.56
sec
pp1024+tg1024
246
tokens/s
20.8
tokens/s
4.22
sec
pp1280+tg3072
241
tokens/s
19.3
tokens/s
5.35
sec
pp384+tg1152
256
tokens/s
21.6
tokens/s
1.54
sec
pp64+tg1024
95
tokens/s
22.1
tokens/s
718
ms
pp16+tg1536
40
tokens/s
21.9
tokens/s
446
ms