TEST #2501 RESULTS
02/01/2026 - 10:53 AM
ACCELERATOR
MODEL
673
tokens/s
generation
19
ms
time to first token
77040
tokens/s
prompt
13898
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
101215
tokens/s
702
tokens/s
12
ms
pp4096+tg256
55415
tokens/s
622
tokens/s
76
ms
pp2048+tg256
94652
tokens/s
657
tokens/s
24
ms
pp2048+tg768
86305
tokens/s
660
tokens/s
25
ms
pp1024+tg1024
119629
tokens/s
676
tokens/s
10
ms
pp1280+tg3072
114772
tokens/s
651
tokens/s
12
ms
pp384+tg1152
97964
tokens/s
682
tokens/s
6
ms
pp64+tg1024
18257
tokens/s
687
tokens/s
5
ms
pp16+tg1536
5147
tokens/s
720
tokens/s
4
ms