TEST #2430 RESULTS
02/01/2026 - 4:19 AM
ACCELERATOR
MODEL
146
tokens/s
generation
123
ms
time to first token
12889
tokens/s
prompt
2481
LocalScore
HOW YOU STACK UP
Explore All ResultsSmolVLM2 256M Video 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
16493
tokens/s
139
tokens/s
69
ms
pp4096+tg256
8028
tokens/s
133
tokens/s
518
ms
pp2048+tg256
13294
tokens/s
146
tokens/s
162
ms
pp2048+tg768
13189
tokens/s
147
tokens/s
163
ms
pp1024+tg1024
20132
tokens/s
145
tokens/s
57
ms
pp1280+tg3072
17126
tokens/s
147
tokens/s
81
ms
pp384+tg1152
20869
tokens/s
154
tokens/s
24
ms
pp64+tg1024
5570
tokens/s
150
tokens/s
17
ms
pp16+tg1536
1304
tokens/s
153
tokens/s
18
ms