TEST #2584 RESULTS
02/10/2026 - 9:29 AM
ACCELERATOR
MODEL
121
tokens/s
generation
218
ms
time to first token
7382
tokens/s
prompt
1600
LocalScore
HOW YOU STACK UP
Explore All ResultsSmolVLM2 500M 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
9919
tokens/s
101
tokens/s
112
ms
pp4096+tg256
4614
tokens/s
114
tokens/s
897
ms
pp2048+tg256
6917
tokens/s
120
tokens/s
304
ms
pp2048+tg768
6866
tokens/s
121
tokens/s
309
ms
pp1024+tg1024
9752
tokens/s
123
tokens/s
113
ms
pp1280+tg3072
8890
tokens/s
120
tokens/s
151
ms
pp384+tg1152
13935
tokens/s
130
tokens/s
35
ms
pp64+tg1024
4200
tokens/s
132
tokens/s
22
ms
pp16+tg1536
1347
tokens/s
127
tokens/s
19
ms