TEST #1003 RESULTS
06/05/2025 - 11:16 PM
ACCELERATOR
MODEL
23.0
tokens/s
generation
4.16
sec
time to first token
302
tokens/s
prompt
119
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X3D 8-Core Processor (znver3)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
372
tokens/s
26.7
tokens/s
2.79
sec
pp4096+tg256
288
tokens/s
12.2
tokens/s
14.29
sec
pp2048+tg256
339
tokens/s
20.6
tokens/s
6.09
sec
pp2048+tg768
339
tokens/s
19.2
tokens/s
6.09
sec
pp1024+tg1024
368
tokens/s
23.3
tokens/s
2.83
sec
pp1280+tg3072
352
tokens/s
17.6
tokens/s
3.67
sec
pp384+tg1152
366
tokens/s
27.3
tokens/s
1.08
sec
pp64+tg1024
135
tokens/s
30.8
tokens/s
503
ms
pp16+tg1536
159
tokens/s
29.2
tokens/s
133
ms