TEST #3466 RESULTS
05/07/2026 - 10:30 PM
ACCELERATOR
MODEL
21.3
tokens/s
generation
8.90
sec
time to first token
171
tokens/s
prompt
74
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
127.9GB
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
187
tokens/s
13.3
tokens/s
6.11
sec
pp4096+tg256
160
tokens/s
11.3
tokens/s
27.42
sec
pp2048+tg256
173
tokens/s
20.4
tokens/s
12.18
sec
pp2048+tg768
173
tokens/s
19.4
tokens/s
12.19
sec
pp1024+tg1024
186
tokens/s
23.4
tokens/s
6.14
sec
pp1280+tg3072
162
tokens/s
17.7
tokens/s
9.33
sec
pp384+tg1152
192
tokens/s
27.0
tokens/s
3.48
sec
pp64+tg1024
45
tokens/s
29.9
tokens/s
3.15
sec
pp16+tg1536
259
tokens/s
29.4
tokens/s
89
ms