TEST #1711 RESULTS
10/28/2025 - 4:23 AM
ACCELERATOR
MODEL
25.9
tokens/s
generation
414
ms
time to first token
3061
tokens/s
prompt
576
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9354 32-Core Processor (znver4)
RAM
377.4GB
OS
Linux
Kernel Release
6.8.0-85-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #85-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 18 15:26:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3986
tokens/s
27.8
tokens/s
293
ms
pp4096+tg256
3369
tokens/s
20.8
tokens/s
1.26
sec
pp2048+tg256
3746
tokens/s
26.8
tokens/s
584
ms
pp2048+tg768
3747
tokens/s
25.0
tokens/s
584
ms
pp1024+tg1024
3992
tokens/s
27.0
tokens/s
293
ms
pp1280+tg3072
3676
tokens/s
23.4
tokens/s
385
ms
pp384+tg1152
3710
tokens/s
27.3
tokens/s
139
ms
pp64+tg1024
1024
tokens/s
27.5
tokens/s
98
ms
pp16+tg1536
302
tokens/s
27.4
tokens/s
89
ms