TEST #3347 RESULTS
04/18/2026 - 1:03 PM
ACCELERATOR
MODEL
3.8
tokens/s
generation
73.28
sec
time to first token
18
tokens/s
prompt
10
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14600K (alderlake)
RAM
31.8GB
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
20
tokens/s
3.9
tokens/s
51.38
sec
pp4096+tg256
17
tokens/s
3.5
tokens/s
238.97
sec
pp2048+tg256
19
tokens/s
3.6
tokens/s
108.60
sec
pp2048+tg768
19
tokens/s
3.6
tokens/s
110.81
sec
pp1024+tg1024
18
tokens/s
3.8
tokens/s
55.66
sec
pp1280+tg3072
19
tokens/s
3.7
tokens/s
67.99
sec
pp384+tg1152
19
tokens/s
4.0
tokens/s
20.18
sec
pp64+tg1024
15
tokens/s
4.0
tokens/s
4.55
sec
pp16+tg1536
14
tokens/s
4.0
tokens/s
1.37
sec