TEST #2455 RESULTS
02/01/2026 - 5:57 AM
ACCELERATOR
MODEL
718
tokens/s
generation
19
ms
time to first token
74446
tokens/s
prompt
14108
LocalScore
HOW YOU STACK UP
Explore All ResultsTinyllama 15M - 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
100742
tokens/s
665
tokens/s
12
ms
pp4096+tg256
56137
tokens/s
592
tokens/s
75
ms
pp2048+tg256
94251
tokens/s
747
tokens/s
23
ms
pp2048+tg768
97235
tokens/s
677
tokens/s
23
ms
pp1024+tg1024
101040
tokens/s
800
tokens/s
11
ms
pp1280+tg3072
111074
tokens/s
733
tokens/s
13
ms
pp384+tg1152
85375
tokens/s
799
tokens/s
6
ms
pp64+tg1024
18342
tokens/s
718
tokens/s
5
ms
pp16+tg1536
5816
tokens/s
734
tokens/s
4
ms