TEST #474 RESULTS
04/07/2025 - 5:21 AM
ACCELERATOR
MODEL
27.4
tokens/s
generation
1.73
sec
time to first token
761
tokens/s
prompt
229
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.13.8-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun, 23 Mar 2025 17:17:30 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
899
tokens/s
26.9
tokens/s
1.17
sec
pp4096+tg256
710
tokens/s
24.0
tokens/s
5.81
sec
pp2048+tg256
817
tokens/s
27.4
tokens/s
2.54
sec
pp2048+tg768
816
tokens/s
27.1
tokens/s
2.55
sec
pp1024+tg1024
880
tokens/s
28.5
tokens/s
1.20
sec
pp1280+tg3072
848
tokens/s
26.3
tokens/s
1.54
sec
pp384+tg1152
865
tokens/s
28.2
tokens/s
478
ms
pp64+tg1024
750
tokens/s
29.2
tokens/s
185
ms
pp16+tg1536
263
tokens/s
28.9
tokens/s
95
ms