TEST #3593 RESULTS
05/21/2026 - 6:24 PM
ACCELERATOR
MODEL
48.0
tokens/s
generation
663
ms
time to first token
1923
tokens/s
prompt
518
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-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
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2278
tokens/s
48.8
tokens/s
471
ms
pp4096+tg256
1902
tokens/s
44.1
tokens/s
2.18
sec
pp2048+tg256
2166
tokens/s
48.3
tokens/s
967
ms
pp2048+tg768
2154
tokens/s
47.9
tokens/s
972
ms
pp1024+tg1024
2308
tokens/s
49.3
tokens/s
464
ms
pp1280+tg3072
2207
tokens/s
46.6
tokens/s
601
ms
pp384+tg1152
2281
tokens/s
49.1
tokens/s
197
ms
pp64+tg1024
1548
tokens/s
49.0
tokens/s
63
ms
pp16+tg1536
465
tokens/s
48.9
tokens/s
54
ms