TEST #1205 RESULTS
07/09/2025 - 10:40 PM
ACCELERATOR
MODEL
8.2
tokens/s
generation
22.24
sec
time to first token
60
tokens/s
prompt
28
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper 3960X 24-Core Processor (znver2)
RAM
62.7GB
OS
Linux
Kernel Release
6.14.2-300.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Apr 10 21:50:55 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
65
tokens/s
8.6
tokens/s
15.78
sec
pp4096+tg256
57
tokens/s
7.6
tokens/s
72.49
sec
pp2048+tg256
61
tokens/s
8.1
tokens/s
33.60
sec
pp2048+tg768
61
tokens/s
7.9
tokens/s
33.70
sec
pp1024+tg1024
63
tokens/s
8.1
tokens/s
16.38
sec
pp1280+tg3072
63
tokens/s
7.9
tokens/s
20.45
sec
pp384+tg1152
65
tokens/s
8.5
tokens/s
5.99
sec
pp64+tg1024
51
tokens/s
8.5
tokens/s
1.37
sec
pp16+tg1536
58
tokens/s
8.3
tokens/s
389
ms