TEST #607 RESULTS
04/08/2025 - 3:35 PM
ACCELERATOR
MODEL
23.0
tokens/s
generation
4.22
sec
time to first token
316
tokens/s
prompt
120
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
63.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
368
tokens/s
26.6
tokens/s
2.82
sec
pp4096+tg256
280
tokens/s
12.2
tokens/s
14.71
sec
pp2048+tg256
335
tokens/s
20.5
tokens/s
6.16
sec
pp2048+tg768
336
tokens/s
19.0
tokens/s
6.15
sec
pp1024+tg1024
369
tokens/s
23.3
tokens/s
2.82
sec
pp1280+tg3072
351
tokens/s
17.5
tokens/s
3.69
sec
pp384+tg1152
376
tokens/s
27.3
tokens/s
1.05
sec
pp64+tg1024
151
tokens/s
31.1
tokens/s
450
ms
pp16+tg1536
277
tokens/s
29.3
tokens/s
85
ms