TEST #572 RESULTS
04/08/2025 - 9:16 AM
ACCELERATOR
MODEL
26.2
tokens/s
generation
1.09
sec
time to first token
1260
tokens/s
prompt
312
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5800X 8-Core Processor (znver3)
RAM
31.2GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1494
tokens/s
27.6
tokens/s
722
ms
pp4096+tg256
1067
tokens/s
23.2
tokens/s
3.88
sec
pp2048+tg256
1346
tokens/s
26.0
tokens/s
1.56
sec
pp2048+tg768
1344
tokens/s
25.9
tokens/s
1.56
sec
pp1024+tg1024
1507
tokens/s
27.0
tokens/s
716
ms
pp1280+tg3072
1466
tokens/s
25.0
tokens/s
911
ms
pp384+tg1152
1547
tokens/s
26.9
tokens/s
284
ms
pp64+tg1024
1219
tokens/s
27.4
tokens/s
119
ms
pp16+tg1536
350
tokens/s
27.1
tokens/s
80
ms