TEST #2514 RESULTS
02/01/2026 - 11:49 PM
ACCELERATOR
MODEL
50.5
tokens/s
generation
664
ms
time to first token
2065
tokens/s
prompt
539
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi 4 Mini Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
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
2420
tokens/s
52.1
tokens/s
444
ms
pp4096+tg256
1786
tokens/s
45.0
tokens/s
2.32
sec
pp2048+tg256
2242
tokens/s
49.8
tokens/s
933
ms
pp2048+tg768
2090
tokens/s
49.4
tokens/s
1000
ms
pp1024+tg1024
2479
tokens/s
51.2
tokens/s
432
ms
pp1280+tg3072
2252
tokens/s
47.9
tokens/s
587
ms
pp384+tg1152
2856
tokens/s
52.7
tokens/s
153
ms
pp64+tg1024
1787
tokens/s
53.2
tokens/s
73
ms
pp16+tg1536
670
tokens/s
52.9
tokens/s
42
ms