TEST #717 RESULTS
04/14/2025 - 7:39 AM
ACCELERATOR
MODEL
20.3
tokens/s
generation
1.79
sec
time to first token
748
tokens/s
prompt
204
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
47GB
OS
Linux
Kernel Release
6.13.10-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Apr 7 19:01:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
871
tokens/s
21.0
tokens/s
1.22
sec
pp4096+tg256
687
tokens/s
18.6
tokens/s
6.01
sec
pp2048+tg256
795
tokens/s
19.9
tokens/s
2.63
sec
pp2048+tg768
789
tokens/s
19.9
tokens/s
2.65
sec
pp1024+tg1024
852
tokens/s
20.5
tokens/s
1.25
sec
pp1280+tg3072
825
tokens/s
19.5
tokens/s
1.60
sec
pp384+tg1152
890
tokens/s
21.0
tokens/s
478
ms
pp64+tg1024
766
tokens/s
21.3
tokens/s
156
ms
pp16+tg1536
257
tokens/s
21.0
tokens/s
109
ms