TEST #752 RESULTS
04/21/2025 - 11:58 PM
ACCELERATOR
MODEL
23.9
tokens/s
generation
565
ms
time to first token
2275
tokens/s
prompt
458
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X 16-Core Processor
RAM
60.4GB
OS
Linux
Kernel Release
6.14.0-061400-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202503241442 SMP PREEMPT_DYNAMIC Mon Mar 24 15:06:01 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2864
tokens/s
26.5
tokens/s
396
ms
pp4096+tg256
2312
tokens/s
19.6
tokens/s
1.83
sec
pp2048+tg256
2644
tokens/s
24.1
tokens/s
817
ms
pp2048+tg768
2708
tokens/s
22.4
tokens/s
799
ms
pp1024+tg1024
2967
tokens/s
23.9
tokens/s
384
ms
pp1280+tg3072
2765
tokens/s
21.0
tokens/s
505
ms
pp384+tg1152
2948
tokens/s
25.4
tokens/s
168
ms
pp64+tg1024
988
tokens/s
26.5
tokens/s
99
ms
pp16+tg1536
283
tokens/s
25.8
tokens/s
93
ms