TEST #838 RESULTS
05/07/2025 - 12:05 PM
ACCELERATOR
MODEL
10.9
tokens/s
generation
976
ms
time to first token
1299
tokens/s
prompt
244
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
31.1GB
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
1749
tokens/s
12.4
tokens/s
665
ms
pp4096+tg256
1479
tokens/s
11.2
tokens/s
2.86
sec
pp2048+tg256
1595
tokens/s
12.1
tokens/s
1.38
sec
pp2048+tg768
1714
tokens/s
11.7
tokens/s
1.28
sec
pp1024+tg1024
1466
tokens/s
9.6
tokens/s
799
ms
pp1280+tg3072
1439
tokens/s
10.6
tokens/s
1.00
sec
pp384+tg1152
1666
tokens/s
10.1
tokens/s
329
ms
pp64+tg1024
463
tokens/s
10.3
tokens/s
235
ms
pp16+tg1536
120
tokens/s
10.1
tokens/s
233
ms