TEST #483 RESULTS
04/07/2025 - 9:41 AM
ACCELERATOR
MODEL
38.8
tokens/s
generation
665
ms
time to first token
2012
tokens/s
prompt
490
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13600K (alderlake)
RAM
31.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2454
tokens/s
39.8
tokens/s
443
ms
pp4096+tg256
1812
tokens/s
35.9
tokens/s
2.29
sec
pp2048+tg256
2168
tokens/s
38.6
tokens/s
972
ms
pp2048+tg768
2185
tokens/s
38.7
tokens/s
963
ms
pp1024+tg1024
2440
tokens/s
39.5
tokens/s
445
ms
pp1280+tg3072
2384
tokens/s
38.3
tokens/s
562
ms
pp384+tg1152
2554
tokens/s
39.4
tokens/s
177
ms
pp64+tg1024
1654
tokens/s
39.6
tokens/s
77
ms
pp16+tg1536
457
tokens/s
39.5
tokens/s
60
ms