TEST #1553 RESULTS
09/24/2025 - 4:02 PM
ACCELERATOR
MODEL
51.8
tokens/s
generation
334
ms
time to first token
4028
tokens/s
prompt
854
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900K (alderlake)
RAM
191.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5030
tokens/s
49.4
tokens/s
223
ms
pp4096+tg256
3678
tokens/s
49.2
tokens/s
1.13
sec
pp2048+tg256
4566
tokens/s
51.8
tokens/s
474
ms
pp2048+tg768
4570
tokens/s
52.3
tokens/s
466
ms
pp1024+tg1024
5208
tokens/s
52.8
tokens/s
215
ms
pp1280+tg3072
4935
tokens/s
51.2
tokens/s
277
ms
pp384+tg1152
5375
tokens/s
53.2
tokens/s
133
ms
pp64+tg1024
2303
tokens/s
52.8
tokens/s
45
ms
pp16+tg1536
585
tokens/s
53.2
tokens/s
45
ms