TEST #2240 RESULTS
01/11/2026 - 7:42 AM
ACCELERATOR
MODEL
99.9
tokens/s
generation
5.47
sec
time to first token
320
tokens/s
prompt
180
LocalScore
HOW YOU STACK UP
Explore All ResultsSmolVLM2 256M Video Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i3-1215U (alderlake)
RAM
11.7GB
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
301
tokens/s
120
tokens/s
3.41
sec
pp4096+tg256
197
tokens/s
61.1
tokens/s
20.76
sec
pp2048+tg256
253
tokens/s
92.9
tokens/s
8.12
sec
pp2048+tg768
254
tokens/s
85.7
tokens/s
8.08
sec
pp1024+tg1024
314
tokens/s
99.5
tokens/s
3.26
sec
pp1280+tg3072
294
tokens/s
76.6
tokens/s
4.36
sec
pp384+tg1152
357
tokens/s
114
tokens/s
1.08
sec
pp64+tg1024
481
tokens/s
128
tokens/s
139
ms
pp16+tg1536
424
tokens/s
121
tokens/s
44
ms