TEST #674 RESULTS
04/10/2025 - 6:43 PM
ACCELERATOR
MODEL
2.2
tokens/s
generation
12.35
sec
time to first token
137
tokens/s
prompt
29
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 14B Instruct AWQ - Q8_0
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
95.9GB
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
98
tokens/s
2.2
tokens/s
10.84
sec
pp4096+tg256
68
tokens/s
1.3
tokens/s
60.67
sec
pp2048+tg256
201
tokens/s
2.4
tokens/s
10.62
sec
pp2048+tg768
196
tokens/s
2.3
tokens/s
10.85
sec
pp1024+tg1024
199
tokens/s
2.3
tokens/s
5.57
sec
pp1280+tg3072
176
tokens/s
2.1
tokens/s
7.74
sec
pp384+tg1152
173
tokens/s
2.3
tokens/s
2.69
sec
pp64+tg1024
98
tokens/s
2.4
tokens/s
1.08
sec
pp16+tg1536
25
tokens/s
2.4
tokens/s
1.06
sec