TEST #2406 RESULTS
01/31/2026 - 6:26 AM
ACCELERATOR
MODEL
657
tokens/s
generation
47
ms
time to first token
38404
tokens/s
prompt
8128
LocalScore
HOW YOU STACK UP
Explore All ResultsTinyLLama - F16
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
46480
tokens/s
657
tokens/s
23
ms
pp4096+tg256
19418
tokens/s
585
tokens/s
213
ms
pp2048+tg256
34189
tokens/s
585
tokens/s
62
ms
pp2048+tg768
34192
tokens/s
660
tokens/s
62
ms
pp1024+tg1024
52061
tokens/s
681
tokens/s
21
ms
pp1280+tg3072
47980
tokens/s
662
tokens/s
28
ms
pp384+tg1152
83616
tokens/s
692
tokens/s
6
ms
pp64+tg1024
22178
tokens/s
700
tokens/s
4
ms
pp16+tg1536
5520
tokens/s
691
tokens/s
4
ms