TEST #746 RESULTS
04/20/2025 - 2:21 AM
ACCELERATOR
MODEL
13.4
tokens/s
generation
5.60
sec
time to first token
357
tokens/s
prompt
95
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2670 v3 @ 2.30GHz (haswell)
RAM
63.9GB
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
381
tokens/s
16.0
tokens/s
2.75
sec
pp4096+tg256
168
tokens/s
7.4
tokens/s
24.52
sec
pp2048+tg256
265
tokens/s
11.2
tokens/s
7.81
sec
pp2048+tg768
265
tokens/s
10.5
tokens/s
7.81
sec
pp1024+tg1024
386
tokens/s
13.1
tokens/s
2.72
sec
pp1280+tg3072
347
tokens/s
9.5
tokens/s
3.76
sec
pp384+tg1152
507
tokens/s
16.1
tokens/s
804
ms
pp64+tg1024
610
tokens/s
19.1
tokens/s
144
ms
pp16+tg1536
283
tokens/s
17.3
tokens/s
94
ms