TEST #75 RESULTS
03/28/2025 - 9:08 PM
ACCELERATOR
MODEL
23.6
tokens/s
generation
1.27
sec
time to first token
1072
tokens/s
prompt
271
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7713 64-Core Processor (znver3)
RAM
503.5GB
OS
Linux
Kernel Release
6.5.0-44-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #44~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jun 18 14:36:16 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1225
tokens/s
24.3
tokens/s
878
ms
pp4096+tg256
949
tokens/s
21.9
tokens/s
4.36
sec
pp2048+tg256
1140
tokens/s
23.4
tokens/s
1.84
sec
pp2048+tg768
1143
tokens/s
23.1
tokens/s
1.84
sec
pp1024+tg1024
1273
tokens/s
23.9
tokens/s
846
ms
pp1280+tg3072
1229
tokens/s
22.8
tokens/s
1.08
sec
pp384+tg1152
1385
tokens/s
24.3
tokens/s
319
ms
pp64+tg1024
1049
tokens/s
24.6
tokens/s
143
ms
pp16+tg1536
251
tokens/s
24.5
tokens/s
103
ms