TEST #150 RESULTS
03/28/2025 - 10:25 PM
ACCELERATOR
MODEL
53.6
tokens/s
generation
521
ms
time to first token
2526
tokens/s
prompt
638
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
125.7GB
OS
Linux
Kernel Release
5.15.0-118-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #128-Ubuntu SMP Fri Jul 5 09:28:59 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3058
tokens/s
54.9
tokens/s
353
ms
pp4096+tg256
2358
tokens/s
49.4
tokens/s
1.76
sec
pp2048+tg256
2779
tokens/s
52.7
tokens/s
756
ms
pp2048+tg768
2776
tokens/s
52.2
tokens/s
757
ms
pp1024+tg1024
3055
tokens/s
54.3
tokens/s
354
ms
pp1280+tg3072
2964
tokens/s
51.8
tokens/s
450
ms
pp384+tg1152
3306
tokens/s
55.2
tokens/s
156
ms
pp64+tg1024
1990
tokens/s
56.0
tokens/s
50
ms
pp16+tg1536
445
tokens/s
55.6
tokens/s
54
ms