TEST #447 RESULTS
04/07/2025 - 12:20 AM
ACCELERATOR
MODEL
23.5
tokens/s
generation
1.21
sec
time to first token
1119
tokens/s
prompt
280
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7713P 64-Core Processor (znver3)
RAM
125.4GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1336
tokens/s
24.0
tokens/s
808
ms
pp4096+tg256
1008
tokens/s
22.0
tokens/s
4.11
sec
pp2048+tg256
1196
tokens/s
23.5
tokens/s
1.76
sec
pp2048+tg768
1191
tokens/s
23.2
tokens/s
1.76
sec
pp1024+tg1024
1326
tokens/s
23.8
tokens/s
814
ms
pp1280+tg3072
1263
tokens/s
22.7
tokens/s
1.06
sec
pp384+tg1152
1399
tokens/s
24.1
tokens/s
317
ms
pp64+tg1024
1056
tokens/s
24.3
tokens/s
139
ms
pp16+tg1536
298
tokens/s
24.2
tokens/s
96
ms