TEST #475 RESULTS
04/07/2025 - 5:26 AM
ACCELERATOR
MODEL
20.5
tokens/s
generation
2.88
sec
time to first token
505
tokens/s
prompt
153
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
602
tokens/s
26.1
tokens/s
1.74
sec
pp4096+tg256
382
tokens/s
3.3
tokens/s
11.02
sec
pp2048+tg256
505
tokens/s
19.6
tokens/s
4.10
sec
pp2048+tg768
502
tokens/s
18.4
tokens/s
4.13
sec
pp1024+tg1024
597
tokens/s
22.2
tokens/s
1.76
sec
pp1280+tg3072
572
tokens/s
12.2
tokens/s
2.28
sec
pp384+tg1152
663
tokens/s
25.9
tokens/s
612
ms
pp64+tg1024
435
tokens/s
29.3
tokens/s
177
ms
pp16+tg1536
284
tokens/s
27.7
tokens/s
85
ms