TEST #73 RESULTS
03/28/2025 - 9:07 PM
ACCELERATOR
MODEL
20.8
tokens/s
generation
954
ms
time to first token
1438
tokens/s
prompt
315
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9374F 32-Core Processor (znver4)
RAM
1511.6GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2005
tokens/s
20.8
tokens/s
559
ms
pp4096+tg256
1239
tokens/s
18.3
tokens/s
3.36
sec
pp2048+tg256
1459
tokens/s
21.2
tokens/s
1.45
sec
pp2048+tg768
1466
tokens/s
20.7
tokens/s
1.44
sec
pp1024+tg1024
2017
tokens/s
20.8
tokens/s
557
ms
pp1280+tg3072
1903
tokens/s
19.8
tokens/s
722
ms
pp384+tg1152
1870
tokens/s
21.8
tokens/s
246
ms
pp64+tg1024
716
tokens/s
22.4
tokens/s
141
ms
pp16+tg1536
266
tokens/s
21.6
tokens/s
104
ms