TEST #149 RESULTS
03/28/2025 - 10:24 PM
ACCELERATOR
MODEL
70.8
tokens/s
generation
335
ms
time to first token
3828
tokens/s
prompt
931
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7B13 64-Core Processor (znver3)
RAM
2003.9GB
OS
Linux
Kernel Release
5.4.0-174-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #193-Ubuntu SMP Thu Mar 7 14:29:28 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5072
tokens/s
72.4
tokens/s
216
ms
pp4096+tg256
3848
tokens/s
65.2
tokens/s
1.08
sec
pp2048+tg256
4490
tokens/s
70.2
tokens/s
470
ms
pp2048+tg768
4367
tokens/s
69.3
tokens/s
484
ms
pp1024+tg1024
4565
tokens/s
71.6
tokens/s
238
ms
pp1280+tg3072
4176
tokens/s
68.5
tokens/s
321
ms
pp384+tg1152
4862
tokens/s
72.8
tokens/s
119
ms
pp64+tg1024
2662
tokens/s
73.8
tokens/s
37
ms
pp16+tg1536
408
tokens/s
73.3
tokens/s
53
ms