TEST #2942 RESULTS
03/01/2026 - 5:52 PM
ACCELERATOR
MODEL
23.4
tokens/s
generation
1.12
sec
time to first token
1205
tokens/s
prompt
293
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
47.9GB
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
1452
tokens/s
23.5
tokens/s
747
ms
pp4096+tg256
1064
tokens/s
22.0
tokens/s
3.89
sec
pp2048+tg256
1294
tokens/s
23.6
tokens/s
1.62
sec
pp2048+tg768
1293
tokens/s
23.4
tokens/s
1.63
sec
pp1024+tg1024
1450
tokens/s
23.9
tokens/s
748
ms
pp1280+tg3072
1412
tokens/s
22.8
tokens/s
948
ms
pp384+tg1152
1599
tokens/s
23.5
tokens/s
282
ms
pp64+tg1024
1027
tokens/s
23.7
tokens/s
121
ms
pp16+tg1536
256
tokens/s
23.9
tokens/s
105
ms