TEST #2568 RESULTS
02/10/2026 - 8:56 AM
ACCELERATOR
MODEL
122
tokens/s
generation
187
ms
time to first token
8946
tokens/s
prompt
1800
LocalScore
HOW YOU STACK UP
Explore All ResultsMTLM1 200M - 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
12050
tokens/s
123
tokens/s
94
ms
pp4096+tg256
5276
tokens/s
106
tokens/s
786
ms
pp2048+tg256
8142
tokens/s
121
tokens/s
260
ms
pp2048+tg768
8053
tokens/s
119
tokens/s
262
ms
pp1024+tg1024
12243
tokens/s
123
tokens/s
93
ms
pp1280+tg3072
10974
tokens/s
118
tokens/s
124
ms
pp384+tg1152
16867
tokens/s
128
tokens/s
31
ms
pp64+tg1024
5335
tokens/s
131
tokens/s
19
ms
pp16+tg1536
1577
tokens/s
130
tokens/s
18
ms