TEST #2578 RESULTS
02/10/2026 - 9:08 AM
ACCELERATOR
MODEL
153
tokens/s
generation
119
ms
time to first token
13033
tokens/s
prompt
2557
LocalScore
HOW YOU STACK UP
Explore All ResultsMobileLLM 125M HF - 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
17230
tokens/s
140
tokens/s
66
ms
pp4096+tg256
8565
tokens/s
145
tokens/s
485
ms
pp2048+tg256
13273
tokens/s
155
tokens/s
161
ms
pp2048+tg768
13342
tokens/s
155
tokens/s
160
ms
pp1024+tg1024
20022
tokens/s
151
tokens/s
58
ms
pp1280+tg3072
17620
tokens/s
154
tokens/s
79
ms
pp384+tg1152
20587
tokens/s
156
tokens/s
26
ms
pp64+tg1024
5190
tokens/s
159
tokens/s
18
ms
pp16+tg1536
1467
tokens/s
158
tokens/s
17
ms