TEST #159 RESULTS
03/28/2025 - 11:20 PM
ACCELERATOR
MODEL
24.9
tokens/s
generation
1.34
sec
time to first token
1037
tokens/s
prompt
268
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2690 v4 @ 2.60GHz (broadwell)
RAM
251.8GB
OS
Linux
Kernel Release
6.8.0-51-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #52-Ubuntu SMP PREEMPT_DYNAMIC Thu Dec 5 13:09:44 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1247
tokens/s
25.5
tokens/s
861
ms
pp4096+tg256
962
tokens/s
22.8
tokens/s
4.30
sec
pp2048+tg256
810
tokens/s
24.4
tokens/s
2.57
sec
pp2048+tg768
1130
tokens/s
24.3
tokens/s
1.85
sec
pp1024+tg1024
1232
tokens/s
25.2
tokens/s
871
ms
pp1280+tg3072
1201
tokens/s
24.1
tokens/s
1.11
sec
pp384+tg1152
1366
tokens/s
25.7
tokens/s
320
ms
pp64+tg1024
1031
tokens/s
26.0
tokens/s
118
ms
pp16+tg1536
353
tokens/s
25.8
tokens/s
83
ms