TEST #2418 RESULTS
01/31/2026 - 9:02 AM
ACCELERATOR
MODEL
75.9
tokens/s
generation
126
ms
time to first token
12204
tokens/s
prompt
1946
LocalScore
HOW YOU STACK UP
Explore All ResultsMonad - 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
16937
tokens/s
76.0
tokens/s
77
ms
pp4096+tg256
8694
tokens/s
73.5
tokens/s
487
ms
pp2048+tg256
14288
tokens/s
79.5
tokens/s
156
ms
pp2048+tg768
15308
tokens/s
78.8
tokens/s
147
ms
pp1024+tg1024
18411
tokens/s
81.2
tokens/s
67
ms
pp1280+tg3072
15126
tokens/s
76.8
tokens/s
96
ms
pp384+tg1152
17250
tokens/s
72.5
tokens/s
33
ms
pp64+tg1024
3014
tokens/s
70.3
tokens/s
36
ms
pp16+tg1536
809
tokens/s
74.6
tokens/s
31
ms
