TEST #3348 RESULTS
04/18/2026 - 4:49 PM
ACCELERATOR
MODEL
6.6
tokens/s
generation
33.31
sec
time to first token
46
tokens/s
prompt
21
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 9850X3D 8-Core Processor
RAM
31.7GB
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
38
tokens/s
6.9
tokens/s
26.78
sec
pp4096+tg256
35
tokens/s
6.0
tokens/s
115.94
sec
pp2048+tg256
37
tokens/s
6.5
tokens/s
54.89
sec
pp2048+tg768
39
tokens/s
6.4
tokens/s
53.10
sec
pp1024+tg1024
58
tokens/s
6.7
tokens/s
17.83
sec
pp1280+tg3072
57
tokens/s
6.4
tokens/s
22.52
sec
pp384+tg1152
58
tokens/s
6.8
tokens/s
6.81
sec
pp64+tg1024
52
tokens/s
6.9
tokens/s
1.37
sec
pp16+tg1536
43
tokens/s
6.8
tokens/s
516
ms