TEST #72 RESULTS
03/28/2025 - 9:06 PM
ACCELERATOR
MODEL
72.2
tokens/s
generation
417
ms
time to first token
2973
tokens/s
prompt
802
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Platinum 8352Y CPU @ 2.20GHz (icelake-server)
RAM
2015.5GB
OS
Linux
Kernel Release
6.5.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue May 7 09:00:52 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3560
tokens/s
74.4
tokens/s
301
ms
pp4096+tg256
3139
tokens/s
66.6
tokens/s
1.32
sec
pp2048+tg256
3415
tokens/s
70.9
tokens/s
614
ms
pp2048+tg768
3417
tokens/s
70.1
tokens/s
614
ms
pp1024+tg1024
3556
tokens/s
73.0
tokens/s
301
ms
pp1280+tg3072
3449
tokens/s
69.5
tokens/s
385
ms
pp384+tg1152
3597
tokens/s
74.6
tokens/s
120
ms
pp64+tg1024
1914
tokens/s
75.5
tokens/s
61
ms
pp16+tg1536
714
tokens/s
74.9
tokens/s
35
ms