TEST #1917 RESULTS
12/08/2025 - 10:47 AM
ACCELERATOR
MODEL
36.5
tokens/s
generation
917
ms
time to first token
1465
tokens/s
prompt
388
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
62.7GB
OS
Linux
Kernel Release
6.18.0-3-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun, 07 Dec 2025 09:39:03 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1705
tokens/s
37.7
tokens/s
627
ms
pp4096+tg256
1322
tokens/s
33.2
tokens/s
3.13
sec
pp2048+tg256
1555
tokens/s
36.0
tokens/s
1.34
sec
pp2048+tg768
1550
tokens/s
35.6
tokens/s
1.35
sec
pp1024+tg1024
1700
tokens/s
37.0
tokens/s
629
ms
pp1280+tg3072
1652
tokens/s
35.0
tokens/s
802
ms
pp384+tg1152
1888
tokens/s
37.9
tokens/s
229
ms
pp64+tg1024
1327
tokens/s
38.5
tokens/s
88
ms
pp16+tg1536
490
tokens/s
38.0
tokens/s
58
ms