TEST #4240 RESULTS
10/02/2026 - 1:07 AM
ACCELERATOR
MODEL
4.8
tokens/s
generation
36.54
sec
time to first token
38
tokens/s
prompt
17
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
63.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
39
tokens/s
5.0
tokens/s
26.26
sec
pp4096+tg256
35
tokens/s
4.3
tokens/s
118.89
sec
pp2048+tg256
36
tokens/s
4.8
tokens/s
57.60
sec
pp2048+tg768
38
tokens/s
4.7
tokens/s
54.03
sec
pp1024+tg1024
39
tokens/s
4.8
tokens/s
26.61
sec
pp1280+tg3072
39
tokens/s
4.6
tokens/s
33.10
sec
pp384+tg1152
40
tokens/s
5.0
tokens/s
9.79
sec
pp64+tg1024
38
tokens/s
5.0
tokens/s
1.87
sec
pp16+tg1536
34
tokens/s
5.0
tokens/s
659
ms