TEST #2485 RESULTS
02/01/2026 - 10:42 AM
ACCELERATOR
MODEL
1492
tokens/s
generation
8
ms
time to first token
167051
tokens/s
prompt
31045
LocalScore
HOW YOU STACK UP
Explore All ResultsTiny_Random_Llama2_New - 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
215072
tokens/s
1354
tokens/s
6
ms
pp4096+tg256
145809
tokens/s
1241
tokens/s
29
ms
pp2048+tg256
216305
tokens/s
1399
tokens/s
10
ms
pp2048+tg768
226709
tokens/s
1452
tokens/s
10
ms
pp1024+tg1024
247092
tokens/s
1564
tokens/s
5
ms
pp1280+tg3072
198693
tokens/s
1473
tokens/s
7
ms
pp384+tg1152
218604
tokens/s
1685
tokens/s
2
ms
pp64+tg1024
28652
tokens/s
1672
tokens/s
3
ms
pp16+tg1536
6521
tokens/s
1583
tokens/s
3
ms