TEST #2383 RESULTS
01/30/2026 - 12:44 PM
ACCELERATOR
MODEL
72.2
tokens/s
generation
560
ms
time to first token
2756
tokens/s
prompt
708
LocalScore
HOW YOU STACK UP
Explore All ResultsEXAONE 3.5 2.4B 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
3255
tokens/s
78.2
tokens/s
328
ms
pp4096+tg256
1932
tokens/s
62.9
tokens/s
2.14
sec
pp2048+tg256
2574
tokens/s
70.5
tokens/s
812
ms
pp2048+tg768
2559
tokens/s
69.0
tokens/s
814
ms
pp1024+tg1024
3150
tokens/s
73.4
tokens/s
338
ms
pp1280+tg3072
2954
tokens/s
67.3
tokens/s
447
ms
pp384+tg1152
4230
tokens/s
75.7
tokens/s
105
ms
pp64+tg1024
3139
tokens/s
76.9
tokens/s
33
ms
pp16+tg1536
1010
tokens/s
75.8
tokens/s
28
ms