TEST #133 RESULTS
03/28/2025 - 10:15 PM
ACCELERATOR
MODEL
64.6
tokens/s
generation
552
ms
time to first token
2317
tokens/s
prompt
647
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v3 @ 2.30GHz (haswell)
RAM
125.8GB
OS
Linux
Kernel Release
5.15.0-134-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #145-Ubuntu SMP Wed Feb 12 20:08:39 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2772
tokens/s
67.1
tokens/s
384
ms
pp4096+tg256
2273
tokens/s
58.2
tokens/s
1.82
sec
pp2048+tg256
2578
tokens/s
63.8
tokens/s
810
ms
pp2048+tg768
2571
tokens/s
62.9
tokens/s
812
ms
pp1024+tg1024
2743
tokens/s
65.3
tokens/s
388
ms
pp1280+tg3072
2661
tokens/s
61.6
tokens/s
496
ms
pp384+tg1152
2829
tokens/s
67.0
tokens/s
166
ms
pp64+tg1024
1928
tokens/s
68.2
tokens/s
48
ms
pp16+tg1536
498
tokens/s
67.6
tokens/s
46
ms