TEST #785 RESULTS
04/29/2025 - 7:40 PM
ACCELERATOR
MODEL
14.1
tokens/s
generation
11.46
sec
time to first token
119
tokens/s
prompt
53
LocalScore
HOW YOU STACK UP
Explore All Resultsqwen2.5-14b-instruct - Q8_0
SYSTEM
CPU
AMD EPYC 9454P 48-Core Processor (znver4)
RAM
251.4GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
124
tokens/s
14.5
tokens/s
8.30
sec
pp4096+tg256
109
tokens/s
13.2
tokens/s
37.62
sec
pp2048+tg256
119
tokens/s
13.9
tokens/s
17.24
sec
pp2048+tg768
119
tokens/s
13.8
tokens/s
17.23
sec
pp1024+tg1024
124
tokens/s
14.2
tokens/s
8.33
sec
pp1280+tg3072
124
tokens/s
13.6
tokens/s
10.42
sec
pp384+tg1152
124
tokens/s
14.4
tokens/s
3.16
sec
pp64+tg1024
123
tokens/s
14.5
tokens/s
586
ms
pp16+tg1536
102
tokens/s
14.5
tokens/s
223
ms