TEST #1873 RESULTS
11/26/2025 - 7:35 PM
ACCELERATOR
MODEL
72.5
tokens/s
generation
304
ms
time to first token
4361
tokens/s
prompt
1013
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
125.7GB
OS
Linux
Kernel Release
6.17.7-200.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Nov 2 17:43:34 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5308
tokens/s
74.8
tokens/s
206
ms
pp4096+tg256
3999
tokens/s
67.2
tokens/s
1.04
sec
pp2048+tg256
4846
tokens/s
72.1
tokens/s
437
ms
pp2048+tg768
4850
tokens/s
71.4
tokens/s
436
ms
pp1024+tg1024
5418
tokens/s
73.6
tokens/s
202
ms
pp1280+tg3072
5220
tokens/s
70.1
tokens/s
259
ms
pp384+tg1152
5750
tokens/s
74.3
tokens/s
93
ms
pp64+tg1024
2998
tokens/s
74.0
tokens/s
35
ms
pp16+tg1536
861
tokens/s
74.9
tokens/s
32
ms