TEST #3344 RESULTS
04/18/2026 - 7:22 AM
ACCELERATOR
MODEL
1.2
tokens/s
generation
34.58
sec
time to first token
37
tokens/s
prompt
11
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2673 v3 @ 2.40GHz (haswell)
RAM
31.9GB
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
1.2
tokens/s
27.27
sec
pp4096+tg256
37
tokens/s
1.0
tokens/s
111.04
sec
pp2048+tg256
41
tokens/s
1.1
tokens/s
51.27
sec
pp2048+tg768
42
tokens/s
1.1
tokens/s
50.08
sec
pp1024+tg1024
43
tokens/s
1.2
tokens/s
24.82
sec
pp1280+tg3072
42
tokens/s
1.1
tokens/s
31.45
sec
pp384+tg1152
40
tokens/s
1.2
tokens/s
10.57
sec
pp64+tg1024
38
tokens/s
1.3
tokens/s
2.44
sec
pp16+tg1536
11
tokens/s
1.2
tokens/s
2.25
sec