TEST #2577 RESULTS
02/10/2026 - 9:07 AM
ACCELERATOR
MODEL
153
tokens/s
generation
116
ms
time to first token
14090
tokens/s
prompt
2645
LocalScore
HOW YOU STACK UP
Explore All ResultsMobileLLM 80M Finetuned - Q6_K
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
17495
tokens/s
155
tokens/s
64
ms
pp4096+tg256
8498
tokens/s
150
tokens/s
490
ms
pp2048+tg256
13408
tokens/s
147
tokens/s
159
ms
pp2048+tg768
13952
tokens/s
148
tokens/s
153
ms
pp1024+tg1024
20912
tokens/s
150
tokens/s
55
ms
pp1280+tg3072
19070
tokens/s
150
tokens/s
73
ms
pp384+tg1152
25328
tokens/s
155
tokens/s
22
ms
pp64+tg1024
6616
tokens/s
160
tokens/s
15
ms
pp16+tg1536
1534
tokens/s
159
tokens/s
16
ms