TEST #118 RESULTS
03/28/2025 - 9:58 PM
ACCELERATOR
MODEL
42.2
tokens/s
generation
1.08
sec
time to first token
1166
tokens/s
prompt
357
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 3600 6-Core Processor (znver2)
RAM
62.7GB
OS
Linux
Kernel Release
6.5.0-21-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 9 13:32:52 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1246
tokens/s
44.8
tokens/s
844
ms
pp4096+tg256
1157
tokens/s
31.6
tokens/s
3.57
sec
pp2048+tg256
1324
tokens/s
41.2
tokens/s
1.57
sec
pp2048+tg768
1326
tokens/s
40.6
tokens/s
1.57
sec
pp1024+tg1024
1411
tokens/s
43.6
tokens/s
748
ms
pp1280+tg3072
1369
tokens/s
38.7
tokens/s
957
ms
pp384+tg1152
1271
tokens/s
45.3
tokens/s
323
ms
pp64+tg1024
1067
tokens/s
47.3
tokens/s
80
ms
pp16+tg1536
323
tokens/s
46.5
tokens/s
70
ms