TEST #494 RESULTS
04/07/2025 - 12:11 PM
ACCELERATOR
MODEL
19.5
tokens/s
generation
3.53
sec
time to first token
404
tokens/s
prompt
131
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i5-12400F (alderlake)
RAM
15.8GB
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
477
tokens/s
24.1
tokens/s
2.19
sec
pp4096+tg256
307
tokens/s
10.3
tokens/s
13.42
sec
pp2048+tg256
416
tokens/s
17.7
tokens/s
4.99
sec
pp2048+tg768
416
tokens/s
15.8
tokens/s
4.98
sec
pp1024+tg1024
470
tokens/s
19.7
tokens/s
2.22
sec
pp1280+tg3072
458
tokens/s
14.1
tokens/s
2.84
sec
pp384+tg1152
523
tokens/s
23.0
tokens/s
770
ms
pp64+tg1024
374
tokens/s
25.0
tokens/s
206
ms
pp16+tg1536
191
tokens/s
25.7
tokens/s
122
ms