TEST #1942 RESULTS
12/15/2025 - 3:43 PM
ACCELERATOR
MODEL
11.2
tokens/s
generation
2.32
sec
time to first token
572
tokens/s
prompt
140
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 8845HS w/ Radeon 780M Graphics (znver4)
RAM
15.3GB
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
685
tokens/s
12.3
tokens/s
1.57
sec
pp4096+tg256
502
tokens/s
3.5
tokens/s
8.44
sec
pp2048+tg256
668
tokens/s
8.1
tokens/s
3.20
sec
pp2048+tg768
666
tokens/s
7.4
tokens/s
3.21
sec
pp1024+tg1024
710
tokens/s
10.7
tokens/s
1.52
sec
pp1280+tg3072
689
tokens/s
6.3
tokens/s
1.95
sec
pp384+tg1152
734
tokens/s
15.1
tokens/s
570
ms
pp64+tg1024
279
tokens/s
20.4
tokens/s
258
ms
pp16+tg1536
218
tokens/s
17.0
tokens/s
107
ms